@article{PangerlSukulRuecketal., author = {Pangerl, Jonas and Sukul, Pritam and R{\"u}ck, Thomas and Fuchs, Patricia and Weigl, Stefan and Miekisch, Wolfram and Bierl, Rudolf and Matysik, Frank-Michael}, title = {An inexpensive UV-LED photoacoustic based real-time sensor-system detecting exhaled trace-acetone}, series = {Photoacoustics}, volume = {38}, journal = {Photoacoustics}, publisher = {Elsevier}, issn = {2213-5979}, doi = {10.1016/j.pacs.2024.100604}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-71279}, pages = {12}, abstract = {n this research we present a low-cost system for breath acetone analysis based on UV-LED photoacoustic spectroscopy. We considered the end-tidal phase of exhalation, which represents the systemic concentrations of volatile organic compounds (VOCs) - providing clinically relevant information about the human health. This is achieved via the development of a CO2-triggered breath sampling system, which collected alveolar breath over several minutes in sterile and inert containers. A real-time mass spectrometer is coupled to serve as a reference device for calibration measurements and subsequent breath analysis. The new sensor system provided a 3σ detection limit of 8.3 ppbV and an NNEA of 1.4E-9 Wcm 1Hz 0.5. In terms of the performed breath analysis measurements, 12 out of 13 fell within the error margin of the photoacoustic measurement system, demonstrating the reliability of the measurements in the field.}, language = {en} } @unpublished{PangerlSukulRuecketal., author = {Pangerl, Jonas and Sukul, Pritam and R{\"u}ck, Thomas and Fuchs, Patricia and Weigl, Stefan and Miekisch, Wolfram and Bierl, Rudolf and Matysik, Frank-Michael}, title = {An Inexpensive Uv-Led Photoacoustic Based Real-Time Sensor-System Detecting Exhaled Trace-Acetone}, publisher = {Elsevier}, doi = {10.2139/ssrn.4724198}, abstract = {In this research we present a low-cost system for breath acetone analysis based on UV-LED photoacoustic spectroscopy. We considered the end-tidal phase of exhalation, which represents the systemic concentrations of volatile organic compounds (VOCs) - providing clinically relevant information about the human health. This is achieved via the development of a CO2-triggered breath sampling system, which collected alveolar breath over several minutes in sterile and inert containers. A real-time mass spectrometer is coupled to serve as a reference device for calibration measurements and subsequent breath analysis. The new sensor system provided a 3σ detection limit of 6.4 ppbV and an NNEA of 1.1E-9 Wcm-1Hz-0.5. In terms of the performed breath analysis measurements, 12 out of 13 fell within the error margin of the photoacoustic measurement system, demonstrating the reliability of the measurements in the field.}, language = {en} } @misc{SpirklRiedNeidhart, author = {Spirkl, Florian and Ried, Michael and Neidhart, Thomas}, title = {CO2-Einsparpotenzial alternativer Bauverfahren am Beispiel von Spezialtiefbau und Rohrgrabenverf{\"u}llung}, series = {Neue Herausforderungen in der Geotechnik - Nachhaltigkeit, Energiewende \& Klimawandel; Beitr{\"a}ge zum 38. Christian Veder Kolloquium : 04. und 05. April 2024, Graz}, journal = {Neue Herausforderungen in der Geotechnik - Nachhaltigkeit, Energiewende \& Klimawandel; Beitr{\"a}ge zum 38. Christian Veder Kolloquium : 04. und 05. April 2024, Graz}, publisher = {Technische Universit{\"a}t Graz}, address = {Graz}, pages = {23 -- 36}, language = {de} } @article{KratzerWestnerStrahringer, author = {Kratzer, Simon and Westner, Markus and Strahringer, Susanne}, title = {Traction with fraction: Strategic IS management in SMEs through Fractional CIOs}, series = {International Journal of Information Systems and Project Management}, volume = {12}, journal = {International Journal of Information Systems and Project Management}, number = {1}, issn = {2182-7788}, doi = {10.12821/ijispm120101}, pages = {5 -- 16}, abstract = {Small and medium-sized enterprises (SMEs) increasingly need to manage nformation technology (IT) effectively in order to remain competitive. However, compared to larger organizations, SMEs often face challenges in terms of resources and employer attractiveness, and regularly do not have the need to employ a Chief Information Officer (CIO) on a full-time basis. To address this issue, a growing number of global experts have begun to provide CIO services on a part-time basis for multiple clients simultaneously. This approach allows SMEs to tap into the expertise of experienced IT leaders at a fraction of the cost and without committing to long-term arrangements. While these professionals, known as "Fractional CIOs", have proven their value in the field, there has been a lack of academic research on this emerging trend. Therefore, we carried out a comprehensive research project between 2020 and 2023, involving 62 Fractional CIOs from 10 countries. The research produced a definition, different types of engagements, and success factors for Fractional CIOs and their engagements. This paper summarizes these findings for a wider audience of academics and practitioners.}, language = {en} } @misc{OPUS4-7129, title = {Sprachassistenten: Anwendungen, Implikationen, Entwicklungen}, editor = {Baumann, Timo and Siegert, Ingo}, address = {Regensburg}, organization = {Verband Deutscher Elektrotechniker. Informationstechnische Gesellschaft}, doi = {10.35096/othr/pub-7129}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-71292}, abstract = {Der zweite ITG-Workshop „Sprachassistenten - Anwendungen, Implikationen, Entwicklungen" fand am 5. M{\"a}rz 2024 in Regensburg statt. Er bot eine organisatorische und inhaltliche Fortf{\"u}hrung des ersten Workshops vor vier Jahren in Magdeburg 2020. Auch in diesem Jahr war er wieder der Konferenz Elektronische Sprachsignalverarbeitung angegliedert. Auf dem Workshop wurden vielf{\"a}ltige und interdisziplin{\"a}re Beitr{\"a}ge in eingeladenen Vortr{\"a}gen und als eingereichte Poster pr{\"a}sentiert. Durch die gute Mischung von Beitragenden sowohl aus der Hochschullandschaft als auch aus der Industrie wurden die verschiedensten Aspekte anwendungsnah diskutiert.}, subject = {Digitaler Sprachassistent}, language = {de} } @inproceedings{Sering, author = {Sering, Konstantin}, title = {Speech/Non-Speech Classification Slightly Improves Synthesis Quality in PAULE}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7095}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70955}, pages = {173 -- 180}, abstract = {One of the tasks PAULE[1, 2] solves is finding suitable control parameter (cp-)trajectories for a given target acoustic. These cp-trajectories can be used to synthesize speech with the articulatory speech synthesizer of the VocalTractLab (VTL) [3]. If the target acoustic contains substantial microphone noise or other background noises, occasionally PAULE optimizes not for the speech in the target, but for this background noises. By adding a speech/non-speech classifier to the feedback and planning-loop in PAULE this resynthesis of background noises should be mitigated. Unfortunately, the improvements were minor, which might be due to uninformative gradients of the classifier. The importance of informative gradients and the use classifiers to adapt PAULE to different tasks are explained and discussed.}, language = {en} } @inproceedings{Hoege, author = {H{\"o}ge, Harald}, title = {The Use of Temporal Features in Cortical Segmentation of Syllables}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7082}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70823}, pages = {70 -- 77}, abstract = {There is high confidence for the hypothesis that in speech perception the cycles of a θ-oscillation segment the auditory signal into syllables [8]. Yet the functionality of the oscillator generating the θ-oscillation is unknown. We follow the finding that, within an auditory scene, speech is perceived as a stream given by temporal coherence [12]. We work with the hypotheses that the θ-oscillator is driven by temporal features providing this coherence. We propose a new temporal feature called O-distance, which detects the onset of a syllable - the starting point to of a θ-cycle-triggered by the temporal distance from to to the instance of the maximal rise of the loudness curve of the vowel. To extract to from the auditory signal, we use the statistical properties of this distance based on the C-center hypothesis [25], which predicts a close temporal relation of the onset consonants to the onset of a vowel. The statistics are derived from reference O-distance extracted from an articulatory database, where the minima and maxima of the loudness are related to maxima and minima of the lower incisor and tongue tip. To judge the quality of the O-distance extracted from the auditory signal, we regard the temporal deviation of the O-distance to the reference O-distance. Currently we achieve a mean deviation of 34ms.}, language = {en} } @inproceedings{Kruspe, author = {Kruspe, Anna}, title = {More than words: Advancements and Challenges in Speech Recognition for Singing}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7074}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70748}, pages = {1 -- 10}, abstract = {This paper addresses the challenges and advancements in speech recognition for singing, a domain distinctly different from standard speech recognition. Singing encompasses unique challenges, including extensive pitch variations, diverse vocal styles, and background music interference. We explore key areas such as phoneme recognition, language identification in songs, keyword spotting, and full lyrics transcription. I will describe some of my own experiences when performing research on these tasks just as they were starting to gain traction, but will also show how recent developments in deep learning and large-scale datasets have propelled progress in this field. My goal is to illuminate the complexities of applying speech recognition to singing, evaluate current capabilities, and outline future research directions.}, language = {en} } @article{SpirklWittlNeidhart, author = {Spirkl, Florian and Wittl, Theresa and Neidhart, Thomas}, title = {Kohlendioxid-Bilanzierung: Rohrgrabenverf{\"u}llung mit Sand vs. ZFSV}, series = {Korrespondenz Abwasser, Abfall}, volume = {71}, journal = {Korrespondenz Abwasser, Abfall}, number = {4}, publisher = {GFA}, address = {Hennef}, doi = {10.3242/kae2024.04.004}, pages = {294 -- 299}, abstract = {Als Alternative zur konventionellen Bettung von Leitungen und Rohren in Sand werden immer h{\"a}ufiger Zeitweise fließf{\"a}hige, Selbstverdichtende Verf{\"u}llbaustoffe (ZFSV) verwendet. Die Bettung in ZFSV kann zu einer Zeit- und Kostenersparnis f{\"u}hren. In diesem Beitrag wird gezeigt, dass die Verwendung von ZFSV zur Rohrgrabenverf{\"u}llung gegen{\"u}ber der konventionellen Sandbettung neben der Schonung der nat{\"u}rlichen Ressourcen zus{\"a}tzlich ein Einsparpotenzial bez{\"u}glich der Treibhausgasemissionen aufweist.}, language = {de} } @unpublished{MendelRueckertWilhelmetal., author = {Mendel, Robert and R{\"u}ckert, Tobias and Wilhelm, Dirk and R{\"u}ckert, Daniel and Palm, Christoph}, title = {Motion-Corrected Moving Average: Including Post-Hoc Temporal Information for Improved Video Segmentation}, doi = {10.48550/arXiv.2403.03120}, pages = {9}, abstract = {Real-time computational speed and a high degree of precision are requirements for computer-assisted interventions. Applying a segmentation network to a medical video processing task can introduce significant inter-frame prediction noise. Existing approaches can reduce inconsistencies by including temporal information but often impose requirements on the architecture or dataset. This paper proposes a method to include temporal information in any segmentation model and, thus, a technique to improve video segmentation performance without alterations during training or additional labeling. With Motion-Corrected Moving Average, we refine the exponential moving average between the current and previous predictions. Using optical flow to estimate the movement between consecutive frames, we can shift the prior term in the moving-average calculation to align with the geometry of the current frame. The optical flow calculation does not require the output of the model and can therefore be performed in parallel, leading to no significant runtime penalty for our approach. We evaluate our approach on two publicly available segmentation datasets and two proprietary endoscopic datasets and show improvements over a baseline approach.}, subject = {Deep Learning}, language = {en} } @article{SouzaJrPachecoPassosetal., author = {Souza Jr., Luis Antonio de and Pacheco, Andr{\´e} G.C. and Passos, Leandro A. and Santana, Marcos Cleison S. and Mendel, Robert and Ebigbo, Alanna and Probst, Andreas and Messmann, Helmut and Palm, Christoph and Papa, Jo{\~a}o Paulo}, title = {DeepCraftFuse: visual and deeply-learnable features work better together for esophageal cancer detection in patients with Barrett's esophagus}, series = {Neural Computing and Applications}, volume = {36}, journal = {Neural Computing and Applications}, publisher = {Springer}, address = {London}, doi = {10.1007/s00521-024-09615-z}, pages = {10445 -- 10459}, abstract = {Limitations in computer-assisted diagnosis include lack of labeled data and inability to model the relation between what experts see and what computers learn. Even though artificial intelligence and machine learning have demonstrated remarkable performances in medical image computing, their accountability and transparency level must be improved to transfer this success into clinical practice. The reliability of machine learning decisions must be explained and interpreted, especially for supporting the medical diagnosis. While deep learning techniques are broad so that unseen information might help learn patterns of interest, human insights to describe objects of interest help in decision-making. This paper proposes a novel approach, DeepCraftFuse, to address the challenge of combining information provided by deep networks with visual-based features to significantly enhance the correct identification of cancerous tissues in patients affected with Barrett's esophagus (BE). We demonstrate that DeepCraftFuse outperforms state-of-the-art techniques on private and public datasets, reaching results of around 95\% when distinguishing patients affected by BE that is either positive or negative to esophageal cancer.}, subject = {Deep Learning}, language = {en} } @inproceedings{RueckertRiederFeussneretal., author = {R{\"u}ckert, Tobias and Rieder, Maximilian and Feussner, Hubertus and Wilhelm, Dirk and R{\"u}ckert, Daniel and Palm, Christoph}, title = {Smoke Classification in Laparoscopic Cholecystectomy Videos Incorporating Spatio-temporal Information}, series = {Bildverarbeitung f{\"u}r die Medizin 2024: Proceedings, German Workshop on Medical Image Computing, March 10-12, 2024, Erlangen}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2024: Proceedings, German Workshop on Medical Image Computing, March 10-12, 2024, Erlangen}, editor = {Maier, Andreas and Deserno, Thomas M. and Handels, Heinz and Maier-Hein, Klaus H. and Palm, Christoph and Tolxdorff, Thomas}, publisher = {Springeer}, address = {Wiesbaden}, doi = {10.1007/978-3-658-44037-4_78}, pages = {298 -- 303}, abstract = {Heavy smoke development represents an important challenge for operating physicians during laparoscopic procedures and can potentially affect the success of an intervention due to reduced visibility and orientation. Reliable and accurate recognition of smoke is therefore a prerequisite for the use of downstream systems such as automated smoke evacuation systems. Current approaches distinguish between non-smoked and smoked frames but often ignore the temporal context inherent in endoscopic video data. In this work, we therefore present a method that utilizes the pixel-wise displacement from randomly sampled images to the preceding frames determined using the optical flow algorithm by providing the transformed magnitude of the displacement as an additional input to the network. Further, we incorporate the temporal context at evaluation time by applying an exponential moving average on the estimated class probabilities of the model output to obtain more stable and robust results over time. We evaluate our method on two convolutional-based and one state-of-the-art transformer architecture and show improvements in the classification results over a baseline approach, regardless of the network used.}, language = {en} } @inproceedings{GutbrodGeislerRauberetal., author = {Gutbrod, Max and Geisler, Benedikt and Rauber, David and Palm, Christoph}, title = {Data Augmentation for Images of Chronic Foot Wounds}, series = {Bildverarbeitung f{\"u}r die Medizin 2024: Proceedings, German Workshop on Medical Image Computing, March 10-12, 2024, Erlangen}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2024: Proceedings, German Workshop on Medical Image Computing, March 10-12, 2024, Erlangen}, editor = {Maier, Andreas and Deserno, Thomas M. and Handels, Heinz and Maier-Hein, Klaus H. and Palm, Christoph and Tolxdorff, Thomas}, publisher = {Springer}, address = {Wiesbaden}, doi = {10.1007/978-3-658-44037-4_71}, pages = {261 -- 266}, abstract = {Training data for Neural Networks is often scarce in the medical domain, which often results in models that struggle to generalize and consequently showpoor performance on unseen datasets. Generally, adding augmentation methods to the training pipeline considerably enhances a model's performance. Using the dataset of the Foot Ulcer Segmentation Challenge, we analyze two additional augmentation methods in the domain of chronic foot wounds - local warping of wound edges along with projection and blurring of shapes inside wounds. Our experiments show that improvements in the Dice similarity coefficient and Normalized Surface Distance metrics depend on a sensible selection of those augmentation methods.}, language = {en} } @misc{OPUS4-7115, title = {Bildverarbeitung f{\"u}r die Medizin 2024}, editor = {Maier, Andreas and Deserno, Thomas M. and Handels, Heinz and Maier-Hein, Klaus H. and Palm, Christoph and Tolxdorff, Thomas}, publisher = {Springer}, address = {Wiesbaden}, isbn = {978-3-658-44037-4}, issn = {1431-472X}, doi = {10.1007/978-3-658-44037-4}, pages = {370}, abstract = {Seit mehr als 25 Jahren ist der Workshop "Bildverarbeitung f{\"u}r die Medizin" als erfolgreiche Veranstaltung etabliert. Ziel ist auch 2024 wieder die Darstellung aktueller Forschungsergebnisse und die Vertiefung der Gespr{\"a}che zwischen Wissenschaftlern, Industrie und Anwendern. Die Beitr{\"a}ge dieses Bandes - viele davon in englischer Sprache - umfassen alle Bereiche der medizinischen Bildverarbeitung, insbesondere die Bildgebung und -akquisition, Segmentierung und Analyse, Visualisierung und Animation, computerunterst{\"u}tzte Diagnose sowie bildgest{\"u}tzte Therapieplanung und Therapie. Hierbei kommen Methoden des maschinelles Lernens, der biomechanischen Modellierung sowie der Validierung und Qualit{\"a}tssicherung zum Einsatz.}, subject = {Bildverarbeitung}, language = {de} } @article{GlavanBelyaevaShamoninChamonine, author = {Glavan, Gašper and Belyaeva, Inna A. and Shamonin (Chamonine), Mikhail}, title = {Transient Response of Macroscopic Deformation of Magnetoactive Elastomeric Cylinders in Uniform Magnetic Fields}, series = {Polymers}, volume = {16}, journal = {Polymers}, number = {5, Special Issue Magnetic Polymer Composites: Design and Application II}, publisher = {MDPI}, address = {Basel, Schweiz}, issn = {2073-4360}, doi = {10.3390/polym16050586}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-71067}, pages = {17}, abstract = {Significant deformations of bodies made from compliant magnetoactive elastomers (MAE) in magnetic fields make these materials promising for applications in magnetically controlled actuators for soft robotics. Reported experimental research in this context was devoted to the behaviour in the quasi-static magnetic field, but the transient dynamics are of great practical importance. This paper presents an experimental study of the transient response of apparent longitudinal and transverse strains of a family of isotropic and anisotropic MAE cylinders with six different aspect ratios in time-varying uniform magnetic fields. The time dependence of the magnetic field has a trapezoidal form, where the rate of both legs is varied between 52 and 757 kA/(s·m) and the maximum magnetic field takes three values between 153 and 505 kA/m. It is proposed to introduce four characteristic times: two for the delay of the transient response during increasing and decreasing magnetic field, as well as two for rise and fall times. To facilitate the comparison between different magnetic field rates, these characteristic times are further normalized on the rise time of the magnetic field ramp. The dependence of the normalized characteristic times on the aspect ratio, the magnetic field slew rate, maximum magnetic field values, initial internal structure (isotropic versus anisotropic specimens) and weight fraction of the soft-magnetic filler are obtained and discussed in detail. The normalized magnetostrictive hysteresis loop is introduced, and used to explain why the normalized delay times vary with changing experimental parameters.}, language = {en} } @article{TauwaldErzingerQuadrioetal., author = {Tauwald, Sandra Melina and Erzinger, Florian and Quadrio, Maurizio and R{\"u}tten, Markus and Stemmer, Christian and Krenkel, Lars}, title = {Tomo-PIV in a patient-specific model of human nasal cavities: a methodological approach}, series = {Measurement Science and Technology}, volume = {35}, journal = {Measurement Science and Technology}, number = {5}, publisher = {IOP Publishing}, doi = {10.1088/1361-6501/ad282c}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70393}, abstract = {The human nose serves as the primary gateway for air entering the respiratory system and plays a vital role in breathing. Nasal breathing difficulties are a significant health concern, leading to substantial healthcare costs for patients. Understanding nasal airflow dynamics is crucial for comprehending respiratory mechanisms. This article presents a detailed study using tomo-Particle Image Velocimetry (PIV) to investigate nasal airflow dynamics while addressing its accuracy. Embedded in the OpenNose project, the work described aims to provide a validation basis for different numerical approaches to upper airway flow. The study includes the manufacturing of a transparent silicone model based on a clinical CT scan, refractive index matching to minimize optical distortions, and precise flow rate adjustments based on physiological breathing cycles. This method allows for spatial high-resolution investigations in different regions of interest within the nasopharynx during various phases of the breathing cycle. The results demonstrate the accuracy of the investigations, enabling detailed analysis of flow structures and gradients. This spatial high-resolution tomo-PIV approach provides valuable insights into the complex flow phenomena occurring during the physiological breathing cycle in the nasopharynx. The study's findings contribute to advancements in non-free-of-sight experimental flow investigation of complex cavities under nearly realistic conditions. Furthermore, reliable and accurate experimental data is crucial for properly validating numerical approaches that compute this patient-specific flow for clinical purposes.}, language = {en} } @inproceedings{RanzenbergerBockletFreisingeretal., author = {Ranzenberger, Thomas and Bocklet, Tobias and Freisinger, Steffen and Georges, Munir and Glocker, Kevin and Herygers, Aaricia and Riedhammer, Korbinian and Schneider, Fabian and Simic, Christopher and Zakaria, Khabbab}, title = {Extending HAnS: Large Language Models For Question Answering, Summarization, And Topic Segmentation In An ML-based Learning Experience Platform}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7103}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-71032}, pages = {219 -- 224}, abstract = {The use of chatbots based on large language models (LLMs) and their impact on society are influencing our learning experience platform Hochschul-Assistenz-System (HAnS). HAnS uses machine learning (ML) methods to support students and lecturers in the online learning and teaching processes [1]. This paper introduces LLM-based features available in HAnS which are using the transcript of our improved Automatic Speech Recognition (ASR) pipeline with an average transcription duration of 45 seconds and an average word error rate (WER) of 6.66\% on over 8 hours of audio data of 7 lecture videos. A LLM-based chatbot could be used to answer questions on the lecture content as the ASR transcript is provided as context. The summarization and topic segmentation uses the LLM to improve our learning experience platform. We generate multiple choice questions using the LLM and the ASR transcript as context during playback in a period of 3 minutes and display them in the HAnS frontend.}, language = {en} } @inproceedings{MousaviSaeedSarfjooGrawunder, author = {Mousavi, Neda and Saeed Sarfjoo, Seyyed and Grawunder, Sven}, title = {Unsupervised emotional pattern recognition using rhythmic and vocal features}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7102}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-71026}, pages = {233 -- 240}, abstract = {In this study, we address the complex dynamics of emotional speech and comprehensively examine the integration of rhythmic and vocal features to recognize emotional patterns. Our exploration is conducted using two German emotional corpora: VMEmo and EmoDB. Employing a combination of supervised methods (here linear discriminant analysis, LDA) and unsupervised techniques (here k-means clustering), we aim to uncover nuanced patterns within the emotional speech in these corpora. The application of LDA highlights salient patterns across different feature sets and focuses on the classification of speakers and prosodic characteristics. In addition, k-means clustering uncovers latent structures that reveal subtle mapping between emotions and speech behavior. Our results suggest that it is possible to cluster data based on prosodic behaviors that are influenced by emotional changes. Although precise mapping to the actual clusters derived from emotional labels could not be fully achieved, the results nonetheless reveal a moderate level of success in this investigation.}, language = {en} } @inproceedings{MousaviGrawunder, author = {Mousavi, Neda and Grawunder, Sven}, title = {The influence of signal segmentation methods on rhythm-bassed speaker recognition}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7101}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-71014}, pages = {225 -- 232}, abstract = {This study investigates the effects of speech segmentation methods on speaker recognition models, particularly with regard to the use of rhythmic feature sets. Using three automatic methods and one manual method on the German database of Kiel corpus, segmentation was performed based on the identification of vowel onsets. Subsequently rhythmic variability indices derived from these intervals were calculated and used for principal component analysis and support vector machine model in order to investigate the variation among speakers. The results underline the influence of signal segmentation methods on speaker recognition models.}, language = {en} } @inproceedings{HarnischHillmann, author = {Harnisch, Philipp L. and Hillmann, Stefan}, title = {Empirical Evaluation of ASR and NLU in a Multimodal Dialogue System for Survey Answering}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7100}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-71007}, pages = {211 -- 218}, abstract = {PROM surveys, used to measure the effect of rehabilitation treatments, are typically filled out on paper, and often suffer from low response rates. Replacing it with a multimodal survey system, supporting touch and speech interaction, could lead to lower hurdles and therefore more data quantity. To do this, it requires task-specific training samples for the Automatic Speech Recognition (ASR) and Natural Language Understanding (NLU) to classify spoken answers into one of the standardized PROM answer options. Due to the lack of training data for medical PROM surveys, we created augmented text samples with each answer option description, combined with different templates. To improve training capabilities, introduce a proper test set, and evaluate the ASR, we also collected 1,797 real voice samples within an empirical study. Further, we incorporate the contextual knowledge of the current question into our NLU architecture by implementing one classifier for every question scale. Our results reveal that training with empirical data leads to better results than augmented data from templates and original answer option descriptions. Because of participant mislabeling of 33\% due to the ambiguity of the task, we receive overall low NLU performances with up to 51.1\% accuracy, and rank-1-accuracy up to 79.3\%. We also find that our implementation of many scale-specific NLU classifiers significantly outperforms one NLU classifier for all labels, that incorporates the same contextual knowledge after the prediction, by 8 percent points.}, language = {en} } @inproceedings{SchubertSinhaKruegeretal., author = {Schubert, Martha and Sinha, Yamini and Kr{\"u}ger, Julia and Siegert, Ingo}, title = {Speech Recognition Errors in ASR Engines and Their Impact on Linguistic Analysis in Psychotherapies}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7099}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70999}, pages = {203 -- 210}, abstract = {Modern intervention planning in psychotherapies may benefit from predicting process relevant psychotherapy constructs by automated speech analysis. One essential step is the extraction of relevant linguistic speech markers by ASR engines, which because of highly sensible data, work offline. We analyze transcription errors from NeMo, Whisper, and Wav2Vec2.0, focusing on their impact on linguistic markers usually requiring high quality transcripts. By utilizing part-of-speech tagging, we examine error occurrences among different word types. The Linguistic Inquiry and Word Count (LIWC) software aids in extracting markers. We highlight challenges in transcribing spontaneous speech, prevalent in therapy, and compare results with the Mozilla CommonVoice dataset, which features read speech.}, language = {en} } @inproceedings{IbrahimYuenXueetal., author = {Ibrahim, Omnia and Yuen, Ivan and Xue, Wei and Andreeva, Bistra and M{\"o}bius, Bernd}, title = {Listener-Oriented Consequences of Predictability-Based Acoustic Adjustment}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7098}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70984}, pages = {196 -- 202}, abstract = {This paper investigated whether predictability-based adjustments in production have listener-oriented consequences in perception. By manipulating the acoustic features of a target syllable in different predictability contexts in German, we tested 40 listeners' perceptual preference for the manipulation. Four source words underwent acoustic modifications on the target syllable. Our results revealed a general preference for the original (unmodified) version over the modified one. However, listeners generally favored the unmodified version more when the source word had a higher predictable context compared to a less predictable one. The results showed that predictability-based adjustments have perceptual consequences and that listeners have predictability-based expectations in perception.}, language = {en} } @inproceedings{BauerZalkowMuelleretal., author = {Bauer, Judith and Zalkow, Frank and M{\"u}ller, Meinard and Dittmar, Christian}, title = {Evaluating the Impact of Prosody Feature Normalization on the Controllability of Pitch in Speech Synthesis}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7097}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70976}, pages = {188 -- 195}, abstract = {Recent neural text-to-speech (TTS) models are able to synthesize highly natural speech signals using deep learning techniques. In practical applications, it can be desirable to have explicit control over the prosody (speech rate, fundamental frequency, and energy) of the synthesized speech. Such controllability can be achieved by adding prosody prediction modules, whose main purpose is to estimate plausible prosody features for each phoneme in the text input. This explicit modeling also allows for changing prosody features at inference time, consequently enabling the adjustment of the prosody in the synthesized audio. In this paper, we evaluate to which extent deliberate manipulation of such prosody features is reflected in the resulting speech audio. We focus particularly on changing the pitch (i.e., fundamental frequency) while applying different normalization strategies.}, language = {en} } @inproceedings{SinhaHintzSiegert, author = {Sinha, Yamini and Hintz, Jan and Siegert, Ingo}, title = {Evaluation of Audio Deepfakes - Systematic Review}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7096}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70960}, pages = {181 -- 187}, abstract = {Generative models for audio are commonly used for music composition, sound effects generation for video game development, audio restoration, voice cloning, etc. The ease of generating indistinguishable fake audio with deep learning poses a major threat to personal privacy, online security, and political discourse. Evaluating the quality and realism of these synthetic utterances is crucial for mitigating the potential for misinformation and harm. To assess this threat, this paper conducts a systematic review, using Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA), on how these deepfake models are currently evaluated. The analysis of 86 papers shows that the majority of the evaluation is conducted on a machine level and highlights a research gap regarding the human perception of deepfakes. This paper explores various methods and perceptual measures employed in assessing audio deepfakes and evaluating their strengths, limitations, and future directions.}, language = {en} } @inproceedings{SchulerNayakSahaetal., author = {Schuler, Christian and Nayak, Shravan and Saha, Debjoy and Baumann, Timo}, title = {Can We See Your Response Before You Speak? Exploring Linguistic Information Found in Inter-Utterance Pauses}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7094}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70949}, pages = {165 -- 172}, abstract = {In this work we assess whether there is information in pauses in-between utterances of the same or different speakers that are predictive of the following speaker's utterance. We present models that connect a person's visual features before they speak to their upcoming utterance. In our experiments we find that outof-the-box pre-trained models can already reach a better-than-chance performance in correlating video embeddings to utterance embeddings. In contrast, models that attempt to predict the first word after the pause do not outperform a unigram model, indicating that our models do not read lips (based e.g. on co-articulation effects) but rather capture more fundamental aspects of the upcoming utterance.}, language = {en} } @inproceedings{VenkateswaranAlFoysalShaiketal., author = {Venkateswaran, Siddarth and Al Foysal, Abdullah and Shaik, Nazeer Basha and B{\"o}ck, Ronald}, title = {Is there Text in Wine? - S+U Learning-based Named Entity Recognition and Triplet Extraction from Wine Aroma Descriptors}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7093}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70931}, pages = {157 -- 164}, abstract = {Wine making is usually considered a domain being far off the processing of speech and language. But in a particular aspect, the domains of speech processing and wine making are related, namely, in the description of wine aromas. These descriptors are used for creating wine expertise as well as more general (advertisement-like) textual representations. In the current paper, we use Natural Language Processing techniques, especially Named Entity Recognition, to identify Aspects and Opinions, reflecting wine characteristics. These are combined with analyses of respective relations (triplet extraction) building Aspect-Opinion-Pairs to establish indicative aroma descriptors, also trying to approach the complex interplay amongst these individual statements. In our experiments, we rely on the Falstaff corpus comprising a huge set of wine descriptions. This results in an average F1 score of around 0.85 for Aspect-Opinion classification. For triplet generation multiple strategies were compared, resulting in an average F1 score of 0.67 in this challenging task. For both tasks we rely only on a handful of manually annotated samples, applying pseudo-labeling methods from seed data to achieve automatic labeling.}, language = {en} } @inproceedings{KettlerHillmann, author = {Kettler, Benedict and Hillmann, Stefan}, title = {Supervised vs. Zero-Shot Learning Automatic Classification of Comments on Educational Videos Using Pre-Trained Language Models}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7092}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70928}, pages = {149 -- 156}, abstract = {Despite the potential of AI, only a small percentage of small and medium-sized enterprises (SMEs) are adopting it due to data issues, expertise gaps, and implementation barriers. Zero-shot learning offers a promising approach for SMEs by minimizing these obstacles. This paper explores the use of zero-shot learning in a real-world NLP classification task on online comments (comparable with intent classification tasks) from the e-learning platform Sofatutor. While finetuning has achieved high accuracy (82.3-86.5\%), zero-shot models have shown lower performance (39.3-61.4\%) due to different label selection, grouping of different scenarios in one class and the type of classification task. Even if the current accuracy is not sufficient for practical application, pre-filtering the data using zeroshot learning might be a promising option for SMEs.}, language = {en} } @inproceedings{VenkateswaranBoeck, author = {Venkateswaran, Siddarth and B{\"o}ck, Ronald}, title = {Can Language Models Behave Like Wine Sommeliers? - Using Multiple Agents To Evaluate The Quality of Wine Descriptors Generated By Llama 2}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7091}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70911}, pages = {141 -- 148}, abstract = {Wines are complex beverages whose taste can be described either numerically or textually, with the former involving the rating of the intensities of different aroma characteristics often with the help of a wine tasting wheel, and the latter with the help of crisp terms often in a poetic fashion. These are often done with the help of wine sommeliers who with one sniff can describe the wine. Usually, each sommelier has a unique style when it comes to textually describing a wine, research has shown that such differences have no negative impact in correctly classifying wines on the basis of their color, grape variety, region etc. Given the recent advancements in the field of Natural Language Processing, especially with the emergence of Large Language Models, we aim to check the capability of Llama 2 in its ability to generate texts pertaining to a specific color of a wine, given a list of aroma intensities as input prompts. In our experiments, we relied on data from Meininger and Falstaff, and on a combination of domain adaptation and pseudo-labeling techniques to create the corpus to train the Llama 2 model on. Also, we relied on a voting scheme of three differently trained classifiers to evaluate the wine-color specific text generation capabilities of Llama 2. Additionally, we employed the services of domain experts to evaluate the quality of a sample set of texts that was generated by Llama 2.}, language = {en} } @inproceedings{BlaabjergKarlsenDecuzardeCastroPiparsetal., author = {Blaabjerg Karlsen, Tobias and Decuzar de Castro, Karl Jhon and Pipars, Emils and Abdel Qader, Iyad Ahed Abdelrahman and Ilinca Sainz, Jose Dumitru and Srugys, Simas and Niebuhr, Oliver}, title = {In Tune With In-Poco? A New Device for Analyzing and Training the Interplay of Body Posture and Charismatic Speech Prosody}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7090}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70900}, pages = {132 -- 140}, abstract = {Our paper introduces a new technology for posture research and training: the INteractive POsture COrrector, IN-POCO. The device warns its users about unfavorable postures when speaking (e.g., sitting in video conferences) and is thus suitable as an aid for rhetoric trainers. In addition, IN-POCO can also collect time-aligned posture and speech signals for researching prosody-posture relationships in the speech sciences. We outline the motivation for the development of IN-POCO and describe the key technical specifications and operational characteristics. The paper concludes with a pilot experiment in which we provide initial evidence that, for a communicative (public) speaking task, posture does indeed affect speech prosody in gender-specific ways - in line with claims of rhetoric trainers and guidebooks, and such that an unfavorable (e.g,, humped) posture can be assumed to reduce the speaker's vocal charisma.}, language = {en} } @inproceedings{JahnkeSonnenWalther, author = {Jahnke, Thorben Frank and Sonnen, Corinna and Walther, Mathias}, title = {Konzept und Evaluation eines Softwaresystems zur Unterst{\"u}tzung der CRM-basierten Sprechwirkungsuntersuchung}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7089}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70893}, pages = {124 -- 131}, abstract = {Das Continuous-Response-Measurement-Verfahren bildet durch die kontinuierliche Bewertungsm{\"o}glichkeit eine wichtige Erg{\"a}nzung zu den g{\"a}ngigen Methoden im Repertoire der Wirkungsforschung. Um diesen Mehrwert voll aussch{\"o}pfen zu k{\"o}nnen, wird als Verfahrensoptimierung die Entwicklung einer Softwarel{\"o}sung vorgestellt. Die {\"U}berpr{\"u}fung des optimierten CRM-Verfahrens erfolgt mittels eines Anwendungsfalls aus der sprechwissenschaftlichen Telekommunikationsforschung im Rahmen eines User-Acceptance-Tests. Dabei wird die Funktionalit{\"a}t und Bedienerfreundlichkeit der entwickelten CRM-Softwarel{\"o}sung unter Beachtung der f{\"u}r die Sprechwirkungsforschung relevanten Kriterien in Form einer A-BStudie getestet. Das Gesamtergebnis des User-Acceptance-Tests f{\"a}llt f{\"u}r die Software Evalue positiv aus. Mit Hilfe der Verfahrensoptimierung des CRM-Verfahrens ist eine variabel einsetzbare und damit vielf{\"a}ltig nutzbare CRM-Softwarel{\"o}sung entstanden.}, language = {de} } @inproceedings{RajasekharLeschanowskyPeters, author = {Rajasekhar, Anjana and Leschanowsky, Anna and Peters, Nils}, title = {Towards Speech Privacy Assessment for Voice Assistants: Exploring Subjective and Objective Measures for Babble Noise}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7088}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70885}, pages = {116 -- 123}, abstract = {The growing prevalence of voice assistants has sparked privacy concerns with respect to content privacy and potential human-based attacks such as eavesdropping which make users feel uncomfortable utilizing them in public. To address these challenges, understanding human privacy perceptions in acoustic environments becomes paramount. This understanding can empower voice assistants to accurately quantify privacy perceptions, adapt conversational patterns, and ultimately enhance human-machine interaction. This study draws inspiration from human-tohuman interactions and previous research on acoustic privacy, to quantify privacy perceptions in environments characterized by babble noise. The primary objective is a comprehensive evaluation of both objective and subjective measures to quantitatively capture privacy perceptions in acoustic environments.}, language = {en} } @inproceedings{BirkholzZhang, author = {Birkholz, Peter and Zhang, Xinyu}, title = {An Investigation of Acoustic Features of the Lower Vocal Tract for Speaker Recognition}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7087}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70870}, pages = {108 -- 115}, abstract = {Speaker recognition systems often use mel-scaled cepstral coefficients (MFCCs) as main features. In contrast to MFCCs, Godoy et al. (2015) proposed a different type of short-term spectral analysis that provides features related to the lower vocal tract (LVT). They are calculated as the ratio of the acoustic shorttime spectra during the closed and open phases of the glottal oscillation cycles based on a pitch-synchronous analysis. These features were suggested to be particularly speaker-specific and might therefore be suitable to substitute or complement MFCCs in speaker recognition systems. The present study investigated the benefit of these features in an i-vector-based speaker recognition system. Using the LVT features alone, the system achieved a speaker recognition rate of 92.3\% with 63 enrolled speakers. When the LVT features were fused with conventional MFCC features, the recognition rate was about equal to the recognition rate using MFCC features alone (> 98\%).}, language = {en} } @inproceedings{DraxlerPoemp, author = {Draxler, Christoph and P{\"o}mp, Julian}, title = {Octra Backend - Eine skalierbare Infrastruktur f{\"u}r Transkriptionsprojekte}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7086}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70867}, pages = {102 -- 107}, abstract = {Octra Backend ist eine portable web-basierte Infrastruktur f{\"u}r Transkriptionsprojekte, die lokal im Feld oder gesch{\"u}tzten Bereichen, im begrenzten Intranet oder weltweit erreichbar im Internet eingesetzt werden kann. Entwicklungsziele waren die Gew{\"a}hrleistung m{\"o}glichst hoher Sicherheitsanforderungen, eine gute Skalierbarkeit sowie eine einfache Installation auch ohne Administratorrechte. Octra Backend ist in Node.js implementiert und f{\"u}r MacOS, Windows und Linux verf{\"u}gbar.}, language = {de} } @inproceedings{HuberLieblWirsching, author = {Huber-Liebl, Markus and Wirsching, G{\"u}nther}, title = {Ein quantenlogisch motivierter Ansatz zur Verarbeitung von {\"A}ußerungs-Bedeutungspaaren}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7085}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70857}, pages = {94 -- 101}, abstract = {Wir repr{\"a}sentieren eine Bedeutung als Liste von Mustersignalen, und unser Ziel ist es, ein weiteres ankommendes Signal damit zu vergleichen. Die Quantenlogik motiviert die Verwendung von Orthogonalprojektoren, um die gesuchte {\"A}hnlichkeit als Projektionswahrscheinlichkeit darzustellen. Die Ergebnisse des quantenlogischen Verfahrens h{\"a}ngen davon ab, in welcher Weise die Signale vorverarbeitet werden. In diesem Aufsatz untersuchen und diskutieren wir vier verschiedene M{\"o}glichkeiten der Vorverarbeitung.}, language = {de} } @inproceedings{FrohnmaierFreisingerHoltetal., author = {Frohnmaier, Mariano and Freisinger, Steffen and Holt, Madeline Faye and Georges, Munir}, title = {NoiSLU: a Noisy speech corpus for Spoken Language Understanding in the Public Transport Domain}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7084}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70848}, pages = {86 -- 93}, abstract = {The use of local public transport requires the barrier-free purchase of a ticket. Travellers who are not proficient in the local language benefit from a multilingual human(ticket)machine voice interaction. This paper presents a nearly parallel audio dataset with 13218 annotated user queries from 20 speakers for English, German and Dutch. The domain-specific speech corpus can be understood as an evaluation dataset for future research in Spoken Language Understanding (SLU) and thus, it enables researches to improve the quality of human-machine interaction applications. Furthermore, we compare the SLU performance of different compositions of Automatic Speech Recognition (ASR) and Natural Language Understanding (NLU) models in baseline experiments on different test datasets.}, language = {en} } @inproceedings{KuhnWolffBorislavov, author = {Kuhn, Johannes and Wolff, Matthias and Borislavov, Borislav}, title = {Epsilon-Verarbeitung bei minimalistischen Grammatiken f{\"u}r Zahlen}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7083}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70830}, pages = {78 -- 85}, abstract = {Um bei Minimalistischen Grammatiken (MG) {\"U}bergenerierung zu vermeiden, kann man Eintr{\"a}ge mit leeren Exponenten (ε-Eintr{\"a}ge) verwenden. Ein Eintrag besteht aus einem Exponenten, der die {\"A}ußerung oder Schrift eines Wortes repr{\"a}sentiert, einer Merkmalsliste, welche die Syntax kodiert und einem λ-Ausdruck, der die Semantik repr{\"a}sentiert. Leere Eintr{\"a}ge f{\"u}hren allerdings zu einer schlechteren Verwendbarkeit der Grammatik f{\"u}r das Parsen. Die vorliegende Arbeit wird ein Umformungsalgorithmus f{\"u}r MGs vorstellen, sodass die Anzahl der ε-Eintr{\"a}ge verringert werden kann, um sie wieder f{\"u}r Parser verwendbar zu machen. Hierzu werden die ε-Eintr{\"a}ge mit den anderen Eintr{\"a}gen vorverarbeitet und dadurch neue Eintr{\"a}ge geschaffen. Die nun {\"u}berfl{\"u}ssigen ε-Eintr{\"a}ge k{\"o}nnen dann problemlos entfernt werden. Der Algorithmus wurde anhand von {\"u}ber 260 Zahlwortgrammatiken getestet.}, language = {de} } @inproceedings{KanyTrouvain, author = {Kany, Valentin and Trouvain, J{\"u}rgen}, title = {Computergest{\"u}tzte Bestimmung des Sprechflusses bei Vorschulkindern}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7081}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70819}, pages = {62 -- 69}, abstract = {Die vorliegende Studie untersucht, inwiefern sich die in der Phonetik verbreiteten Skripte zur automatisierten Feststellung von verschiedenen Aspekten des Sprechflusses von de Jong et al. zur Beurteilung des Sprachstands bei Kindern eignen und in welcher Art und Weise die Methodik angepasst werden k{\"o}nnte. Dazu wurden Sprachdaten von Vorschulkindern mit Deutsch als Muttersprache bzw. als Zweitsprache mithilfe eines Serious Game zur Sprachstandserhebung elizitiert. Die Audiodaten wurden bez{\"u}glich Artikulationsrate, Pausen und F{\"u}llpartikeln sowohl automatisiert durch die Skripte als auch manuell annotiert. Die Ergebnisse zeigen, dass sich die Skripte zur Ermittlung der Artikulationsrate mit einer relativ hohen {\"U}bereinstimmung mit der manuellen Ermittlung zur Verwendung in Sprachstandserhebungsverfahren eignen. Auch die automatische Erkennung von Sprechpausen weist einen hohen Precision-Wert auf und k{\"o}nnte als Instrument in Sprachstandserhebungen verwendet werden. Eine solche Verwendung w{\"u}rde mit einer Erweiterung um die hier vorgestellte manuelle Methode zum Annotieren von disfluenten und nicht disfluenten Pausen profitieren. Bei den F{\"u}llpartikeln stellte sich die automatisierte Klassifizierung hingegen als weniger geeignet heraus. Hier wurde keine hohe {\"U}bereinstimmung mit der menschlichen Annotation festgestellt. Um in der Praxis Verwendung finden zu k{\"o}nnen, muss diese Methode noch erweitert werden, zum Beispiel durch Miteinbeziehen der Pausenerkennung.}, language = {de} } @inproceedings{PossamaideMenezesKleinerKainzetal., author = {Possamai de Menezes, Jo{\~a}o V{\´i}tor and Kleiner, Christian and Kainz, Marie-Anne and Echternach, Matthias and Birkholz, Peter}, title = {Synchrony of Glottal Area Waveform Parameters During the Production of Obstruents in Vowel Context}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7080}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70808}, pages = {54 -- 61}, abstract = {Obstruents are phonemes which require partial or total obstruction of airflow through the vocal tract. Their articulation also requires adjustments of the laryngeal settings, e. g., an abduction gesture to stop vocal fold vibration for voiceless obstruents. This study investigated the laryngeal settings during the production of voiced and voiceless obstruents in vowel context to analyze the degree of synchrony of the involved glottal gestures. High-speed laryngoscopy images were used to determine the glottal area waveform, from which the time functions of the parameters open quotient (OQ), fundamental frequency (f0), and AC and DC amplitude (ACA and DCA) were calculated and analyzed. Significant correlations were found between all pairs of parameters, with strong correlations between some of them, e.g. Open Quotient and AC Amplitude. Correlations were also either consistently positive or negative for specific pairs of parameters across all investigated phonemes. These results could point to consistent patterns in laryngeal gestures that could enhance articulatory speech synthesis.}, language = {en} } @inproceedings{EliseevaYuenMoebius, author = {Eliseeva, Uliana and Yuen, Ivan and M{\"o}bius, Bernd}, title = {Perception of Formant Distortion in German Words and Non-words}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7079}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70793}, pages = {46 -- 53}, abstract = {Concatenative text-to-speech (TTS) systems remain a widely used cheaper alternative to neural TTS systems. Yet concatenation of prerecorded units entails some drawbacks, such as spectral distortion, the perceptual consequences of which remain unclear. In an attempt to bridge this gap, our study focused on the effect of spectral distortion in vowel formants on perceived speech quality in naturally-read manipulated German words as well as non-words. More specifically, we explored the distortion effect on a varying number of affected formants, at different magnitude and directionality in two corner vowels /a:/ and /i:/. The results indicate that single formant manipulations have a less pronounced effect on the listeners' perception compared to multiple formant perturbations. The threshold at which the distortion became generally audible was estimated to lie between 0.4 and 1.0 bandwidth. The directionality of the distortion was not found to be significant.}, language = {en} } @inproceedings{KisserBuschSiegert, author = {Kisser, Lea and Busch, Matthias and Siegert, Ingo}, title = {Review of Usage and Potentials of Conversational Interfaces at Universities and in Students Daily Lifes}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7078}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70789}, pages = {38 -- 45}, abstract = {The continuous advancement of digitization extends beyond educational institutions, giving rise to numerous innovations, particularly in the realm of study information [1]. One avenue for incorporating digital methodologies involves leveraging conversational agents (CAs) [2], serving as interactive interfaces bridging the gap between humans and computers. In the broader context, conversational agents are gaining prominence, offering several benefits to their users. The overarching goal is to comprehensively assist users through these intelligent systems. Consequently, exploring existing university chatbots becomes imperative to discern the areas where they excel. This research aims to scrutinize diverse chatbot systems, delving into their use cases and the challenges they encounter, employing a systematic review. Here it turns out that chatbots support universities the most in the fields of administration, e-learning and mental health. Furthermore, the study will investigate practical experiences on the potential applications and implementation of these systems in university settings, incorporating insights from an online survey and interviews, both made with experts. Here it comes to conclusion that preparation in relation to a chatbot implementation is the key factor to success. Otherwise, a failed system is nearly impossible to be saved, once users lost trust in the system. Therefore, carefully made preparations in the technical and organisational field are necessary to provide a helpful assistant.}, language = {en} } @inproceedings{WaltherZeunerRykova, author = {Walther, Mathias and Zeuner, Elisabeth and Rykova, Eugenia}, title = {Interaktionsverhalten eines Avatars im digitalen sprachtherapeutischen Setting}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7077}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70774}, pages = {30 -- 37}, abstract = {Die Therapie-App aphaDIGITAL wird im Rahmen eines Forschungsprojekts entwickelt, um Menschen mit Aphasie im h{\"a}uslichen Umfeld zu unterst{\"u}tzen. Das Projekt kombiniert bew{\"a}hrte Therapiemethoden mit digitalen Technologien, einschließlich k{\"u}nstlicher Intelligenz und einem interaktiven Avatar namens Eva. Dieser Artikel betrachtet die Analyse und Entwicklung der Interaktionsmechanismen, die f{\"u}r eine digitale Assistenz von Aphasietherapie den gr{\"o}ßten Einfluss haben. Es wurden dazu reale Therapiesitzungen zwischen sprachgesch{\"a}digten Menschen und ihren Therapeuten konversationsanalytisch nach spezifischen Merkmalen untersucht. Darauf aufbauend wurde durch manuelle Animation ein prototypisches Mundbild modelliert und ein eigenes Artikulationssystem konzipiert, um ein entsprechend authentisches Modell der deutschen Artikulations- und Koartikulationsmuster abzubilden.}, language = {de} } @inproceedings{HillmannKowolAhmadetal., author = {Hillmann, Stefan and Kowol, Philine and Ahmad, Adnan and Tang, Ruochen and M{\"o}ller, Sebastian}, title = {Usability and User Experience of a Chatbot for Student Support}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7076}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70760}, pages = {22 -- 29}, abstract = {This paper describes the usability evaluation of the parts of the CHATU chatbot. The evaluation was conducted with 21 participants. A focus of this paper is the description of the carefully designed evaluation procedure, which aims to avoid textual priming of the participants. The general evaluation procedure can be applied to other speech- or text-based conversational systems, and additional material is provided. The evaluation results show that the usability and user experience of CHATU are positively rated. However, the naturalness and novelty of the interaction are not optimal, and the potential influence of users' experience with LLMs on the evaluation is discussed.}, language = {en} } @article{KrysztofMieraUrbańskietal., author = {Krysztof, Michał and Miera, Paweł and Urbański, Paweł and Grzebyk, Tomasz and Hausladen, Matthias and Schreiner, Rupert}, title = {Integrated silicon electron source for high vacuum microelectromechanical system devices}, series = {Journal of Vacuum Science \& Technology B}, volume = {42}, journal = {Journal of Vacuum Science \& Technology B}, number = {2}, publisher = {AIP Publishing}, issn = {2166-2746}, doi = {10.1116/6.0003385}, abstract = {The article presents the process of developing a silicon electron source designed for high-vacuum microelectromechanical system (HV MEMS) devices, i.e., MEMS electron microscope and MEMS x-ray source. Technological constraints and issues of such an electron source are explained. The transition from emitters made of carbon nanotubes to emitters made of pure silicon is described. Overall, the final electron source consists of a silicon tip emitter and a silicon gate electrode integrated on the same glass substrate. The source generates an electron beam without any carbon nanotube coverage. It generates a high and stable electron current and works after the final bonding process of an HV MEMS device.}, language = {en} } @inproceedings{SchafferSchwaetzerRussetal., author = {Schaffer, Stefan and Schwaetzer, Eva and Ruß, Aaron and Gustke, Oliver}, title = {Chatbot in the Museum - A Field Study of User Experience and Modality Usage}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7075}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70758}, pages = {14 -- 21}, abstract = {This paper describes a field study conducted with a museum chatbot at the St{\"a}del Museum Frankfurt. The chatbot uses the BERT language model for natural language processing and can be operated via touchscreen as well as via speech input. Prior to the study, hypotheses regarding the user experience of the system were formulated and a system-specific questionnaire was designed, which was used to inquire (among other things) about the perceived quality of the speech output and the frequency of audio guide use in museums. During the interaction with the chatbot, log data was collected and stored in the back-end system. The results show a significant correlation between perceived speech quality and user experience. An exploratory data analysis revealed that participants who used only speech input rated the system as significantly more stimulating than participants who used only touch input. Touch input turned out to be the most efficient input modality in terms of answer correctness and was rated highest regarding pragmatic quality. Interestingly touch input was preferred by younger participants. We discuss our findings and conclude that speech interaction should be seriously considered to create engaging conversational user experiences in museums.}, language = {en} } @article{PongratzTixWolfrumetal., author = {Pongratz, Christian and Tix, Janek and Wolfrum, Johannes and Gerke, Steffen and Ehrlich, Ingo and Br{\"u}nig, Michael}, title = {Test Setup for Investigating the Impact Behavior of Biaxially Prestressed Composite Laminates}, series = {Experimental Techniques}, journal = {Experimental Techniques}, publisher = {Springer Nature}, issn = {0732-8818}, doi = {10.1007/s40799-024-00701-4}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70355}, pages = {14 S.}, abstract = {Instrumented impact testing and compression-after-impact testing are important to adequately qualify material behavior and safely design composite structures. However, the stresses to which fiber-reinforced plastic components are typically subjected in practice are not considered in the impact test methods recommended in guidelines or standards. In this paper, a test setup for investigating the impact behavior of composite specimens under plane uniaxial and biaxial preloading is presented. For this purpose, a special test setup consisting of a biaxial testing machine and a specially designed drop-weight tower was developed. The design decisions were derived from existing guidelines and standards with the aim of inducing barely visible impact damage in laminated carbon fiber-reinforced plastic specimens. Several measurement systems have been integrated into the setup to allow comprehensive observation of the impact event and specimen behavior. A feasibility test was performed with biaxially prestressed carbon fiber-reinforced plastic specimens in comparison with unstressed reference tests. The compressive-tensile prestressing resulted in lower maximum contact forces, higher maximum deflections, higher residual deflections and a different damage pattern, which was investigated by light microscopic analysis. Finally, the functionality of the experimental setup is discussed, and the results seem to indicate that the test setup and parameters were properly chosen to investigate the effect of prestresses on the impacts behavior of composite structures, in particular for barely visible subsequent damages.}, subject = {Faserverbundwerkstoff}, language = {en} } @misc{OlbrichPongratzBierletal., author = {Olbrich, Florian and Pongratz, Christian and Bierl, Rudolf and Ehrlich, Ingo}, title = {Method and System for Evaluating a Structural Integrity of an Aerial Vehicle}, language = {en} } @article{HartmannNieberlePalmetal., author = {Hartmann, Robin and Nieberle, Felix and Palm, Christoph and Br{\´e}bant, Vanessa and Prantl, Lukas and Kuehle, Reinald and Reichert, Torsten E. and Taxis, Juergen and Ettl, Tobias}, title = {Utility of Smartphone-based Three-dimensional Surface Imaging for Digital Facial Anthropometry}, series = {JPRAS Open}, volume = {39}, journal = {JPRAS Open}, publisher = {Elsevier}, doi = {10.1016/j.jpra.2024.01.014}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70348}, pages = {330 -- 343}, abstract = {Background The utilization of three-dimensional (3D) surface imaging for facial anthropometry is a significant asset for patients undergoing maxillofacial surgery. Notably, there have been recent advancements in smartphone technology that enable 3D surface imaging. In this study, anthropometric assessments of the face were performed using a smartphone and a sophisticated 3D surface imaging system. Methods 30 healthy volunteers (15 females and 15 males) were included in the study. An iPhone 14 Pro (Apple Inc., USA) using the application 3D Scanner App (Laan Consulting Corp., USA) and the Vectra M5 (Canfield Scientific, USA) were employed to create 3D surface models. For each participant, 19 anthropometric measurements were conducted on the 3D surface models. Subsequently, the anthropometric measurements generated by the two approaches were compared. The statistical techniques employed included the paired t-test, paired Wilcoxon signed-rank test, Bland-Altman analysis, and calculation of the intraclass correlation coefficient (ICC). Results All measurements showed excellent agreement between smartphone-based and Vectra M5-based measurements (ICC between 0.85 and 0.97). Statistical analysis revealed no statistically significant differences in the central tendencies for 17 of the 19 linear measurements. Despite the excellent agreement found, Bland-Altman analysis revealed that the 95\% limits of agreement between the two methods exceeded ±3 mm for the majority of measurements. Conclusion Digital facial anthropometry using smartphones can serve as a valuable supplementary tool for surgeons, enhancing their communication with patients. However, the proposed data suggest that digital facial anthropometry using smartphones may not yet be suitable for certain diagnostic purposes that require high accuracy.}, language = {en} } @misc{RueckertRueckertPalm, author = {R{\"u}ckert, Tobias and R{\"u}ckert, Daniel and Palm, Christoph}, title = {Corrigendum to "Methods and datasets for segmentation of minimally invasive surgical instruments in endoscopic images and videos: A review of the state of the art" [Comput. Biol. Med. 169 (2024) 107929]}, series = {Computers in Biology and Medicine}, journal = {Computers in Biology and Medicine}, publisher = {Elsevier}, doi = {10.1016/j.compbiomed.2024.108027}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70337}, pages = {1}, abstract = {The authors regret that the SAR-RARP50 dataset is missing from the description of publicly available datasets presented in Chapter 4.}, language = {en} } @article{HammerNunesHammeretal., author = {Hammer, Simone and Nunes, Danilo Weber and Hammer, Michael and Zeman, Florian and Akers, Michael and G{\"o}tz, Andrea and Balla, Annika and Doppler, Michael Christian and Fellner, Claudia and Da Platz Batista Silva, Natascha and Thurn, Sylvia and Verloh, Niklas and Stroszczynski, Christian and Wohlgemuth, Walter Alexander and Palm, Christoph and Uller, Wibke}, title = {Deep learning-based differentiation of peripheral high-flow and low-flow vascular malformations in T2-weighted short tau inversion recovery MRI}, series = {Clinical hemorheology and microcirculation}, journal = {Clinical hemorheology and microcirculation}, edition = {Pre-press}, publisher = {IOP Press}, doi = {10.3233/CH-232071}, pages = {1 -- 15}, abstract = {BACKGROUND Differentiation of high-flow from low-flow vascular malformations (VMs) is crucial for therapeutic management of this orphan disease. OBJECTIVE A convolutional neural network (CNN) was evaluated for differentiation of peripheral vascular malformations (VMs) on T2-weighted short tau inversion recovery (STIR) MRI. METHODS 527 MRIs (386 low-flow and 141 high-flow VMs) were randomly divided into training, validation and test set for this single-center study. 1) Results of the CNN's diagnostic performance were compared with that of two expert and four junior radiologists. 2) The influence of CNN's prediction on the radiologists' performance and diagnostic certainty was evaluated. 3) Junior radiologists' performance after self-training was compared with that of the CNN. RESULTS Compared with the expert radiologists the CNN achieved similar accuracy (92\% vs. 97\%, p = 0.11), sensitivity (80\% vs. 93\%, p = 0.16) and specificity (97\% vs. 100\%, p = 0.50). In comparison to the junior radiologists, the CNN had a higher specificity and accuracy (97\% vs. 80\%, p <  0.001; 92\% vs. 77\%, p <  0.001). CNN assistance had no significant influence on their diagnostic performance and certainty. After self-training, the junior radiologists' specificity and accuracy improved and were comparable to that of the CNN. CONCLUSIONS Diagnostic performance of the CNN for differentiating high-flow from low-flow VM was comparable to that of expert radiologists. CNN did not significantly improve the simulated daily practice of junior radiologists, self-training was more effective.}, language = {en} } @article{HausladenBuchnerBartletal., author = {Hausladen, Matthias and Buchner, Philipp and Bartl, Mathias and Bachmann, Michael and Schreiner, Rupert}, title = {Integrated multichip field emission electron source fabricated by laser-micromachining and MEMS technology}, series = {Journal of Vacuum Science \& Technology B}, volume = {42}, journal = {Journal of Vacuum Science \& Technology B}, number = {1}, publisher = {AIP Publishing}, doi = {10.1116/6.0003233}, abstract = {In this work, high-current field emission electron source chips were fabricated using laser-micromachining and MEMS technology. The resulting chips were combined with commercially available printed circuit boards (PCBs) to obtain a multichip electron source. By controlling the separate electron sources using an external current control circuit, we were able to divide the desired total current evenly across the individual chips deployed in the PCB-carrier. In consequence, we were able to show a decreased degradation due to the reduced current load per chip. First, a single electron source chip was measured without current regulation. A steady-state emission current of 1 mA with a high stability of ±1.3\% at an extraction voltage of 250 V was observed. At this current level, a mean degradation slope of -0.7 μA/min with a nearly perfect transmission ratio of 99\% ± 0.4\% was determined. The measurements of a fully assembled multichip PCB-carrier electron source, using a current control circuit for regulation, showed that an even distribution of the desired total current led to a decreased degradation. This was determined by the increase in the required extraction voltage over time. For this purpose, two current levels were applied to the electron source chips of the PCB-carrier using an external current control circuit. First, 300 μA total current was evenly distributed among the individual electron source chips followed by the emission of 300 μA per electron source chip. This allows the observation of the influence of a distributed and nondistributed total current, carried by the electron source chips. Thereby, we obtained an increase in the mean degradation slope from +0.011 V/min (300 μA distributed) to +0.239 V/min (300 μA per chip), which is approximately 21 times higher. Moreover, our current control circuit improved the current stability to under 0.1\% for both current levels, 300 μA distributed and 300 μA per chip.}, language = {en} } @inproceedings{FuhrmannNiemetz, author = {Fuhrmann, Thomas and Niemetz, Michael}, title = {Analysis and Improvement of Engineering Exams Toward Competence Orientation by Using an AI Chatbot}, series = {Towards a Hybrid, Flexible and Socially Engaged Higher Education: Proceedings of the 26th International Conference on Interactive Collaborative Learning (ICL2023), Volume 1}, booktitle = {Towards a Hybrid, Flexible and Socially Engaged Higher Education: Proceedings of the 26th International Conference on Interactive Collaborative Learning (ICL2023), Volume 1}, publisher = {Springer Nature}, address = {Cham}, isbn = {9783031519789}, issn = {2367-3370}, doi = {10.1007/978-3-031-51979-6_42}, pages = {403 -- 411}, abstract = {ChatGPT is currently one of the most advanced general chatbots. This development leads to diverse challenges in higher education, like new forms of teaching and learning, additional exam methods, new possibilities for plagiarism, and many more topics. On the other side with the development of advanced AI tools, pure knowledge will be less and less important, and demands from industry will change toward graduates with higher competencies. Education has therefore to be changed from knowledge-centered toward competence centered. The goal of this article is to use ChatGPT for analyzing and improving the competence orientation of exams in engineering education. The authors use ChatGPT to analyze exams from different engineering subjects to evaluate the performance of this chatbot and draw conclusions about the competence orientation of the tested exams. The obtained information is used to develop ideas for increasing the competence orientation of exams. From this analysis, it is visible that ChatGPT gives good performance mainly where knowledge is tested. It has, however, much more problems with transfer questions or tasks where students need creativity or complex insights for finding new solutions. Based on this result, exams and also lectures can be optimized toward competence orientation.}, language = {en} } @article{JohnsonAnwerXuetal., author = {Johnson, Ebin M. and Anwer, Shakil and Xu, Yongchao and Fuhrmann, Thomas and Mandl, Roland}, title = {Contactless Low-Cost Position Sensor using a D-Shaped Polymer Optical Fiber}, series = {IEEE Sensors Journal}, journal = {IEEE Sensors Journal}, publisher = {IEEE}, doi = {10.1109/JSEN.2023.3348127}, abstract = {This article describes a contactless fiber-optic position sensor. It comprises a Polymer Optical Fiber that is grinded to form a D-shaped cross-section with an exposed fiber core. This sensor has two photodiodes at both fiber ends to measure the emitted light intensity. Light is coupled using a red LED at the side face into the exposed core of the fiber at a defined position. The position of the LED at the length of the fiber is measured by calculating the optical power quotient measured by both photodiodes. To test this sensor, Polymer Optical Fibers with different side surface roughness are produced and qualified. Measurements show that the optical power quotient is reproducible and nearly linear over the length of the fiber. It is also seen that the fiber attenuation increases when grinding the fiber side-face with rougher sandpaper. Position measurements show an absolute position error of this sensor in the range of a few millimeters. Microscope images show surface defects along the polished side face of the fiber that are expected to lead to a nonuniform attenuation along the fiber and cause the position errors. Overall, it is proven that this sensor principle works as a contactless low-cost position sensor for short distances with an absolute position standard deviation error lower than 1 mm.}, language = {en} } @incollection{HeeseWaechter, author = {Heese, Carl and W{\"a}chter, F.}, title = {Soziale Arbeit in der Therapie chronischer Schmerzen}, series = {Die Nachhaltigkeitsziele der UN im Spiegel der Wissenschaft: Beispiele aus der Sozial- und Gesundheitsforschung}, booktitle = {Die Nachhaltigkeitsziele der UN im Spiegel der Wissenschaft: Beispiele aus der Sozial- und Gesundheitsforschung}, editor = {Heese, Carl and Sch{\"u}tz, Sandra and Obergrießer, Stefanie}, publisher = {Springer VS}, address = {Wiesbaden}, language = {de} } @article{RueckertRueckertPalm, author = {R{\"u}ckert, Tobias and R{\"u}ckert, Daniel and Palm, Christoph}, title = {Methods and datasets for segmentation of minimally invasive surgical instruments in endoscopic images and videos: A review of the state of the art}, series = {Computers in Biology and Medicine}, volume = {169}, journal = {Computers in Biology and Medicine}, publisher = {Elsevier}, address = {Amsterdam}, doi = {10.1016/j.compbiomed.2024.107929}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-69830}, pages = {24}, abstract = {In the field of computer- and robot-assisted minimally invasive surgery, enormous progress has been made in recent years based on the recognition of surgical instruments in endoscopic images and videos. In particular, the determination of the position and type of instruments is of great interest. Current work involves both spatial and temporal information, with the idea that predicting the movement of surgical tools over time may improve the quality of the final segmentations. The provision of publicly available datasets has recently encouraged the development of new methods, mainly based on deep learning. In this review, we identify and characterize datasets used for method development and evaluation and quantify their frequency of use in the literature. We further present an overview of the current state of research regarding the segmentation and tracking of minimally invasive surgical instruments in endoscopic images and videos. The paper focuses on methods that work purely visually, without markers of any kind attached to the instruments, considering both single-frame semantic and instance segmentation approaches, as well as those that incorporate temporal information. The publications analyzed were identified through the platforms Google Scholar, Web of Science, and PubMed. The search terms used were "instrument segmentation", "instrument tracking", "surgical tool segmentation", and "surgical tool tracking", resulting in a total of 741 articles published between 01/2015 and 07/2023, of which 123 were included using systematic selection criteria. A discussion of the reviewed literature is provided, highlighting existing shortcomings and emphasizing the available potential for future developments.}, subject = {Deep Learning}, language = {en} } @incollection{Rudolph, author = {Rudolph, Clarissa}, title = {Gleichstellungspolitik als politikwissenschaftliche Praxis}, series = {Handbuch Politik und Geschlecht}, booktitle = {Handbuch Politik und Geschlecht}, editor = {Klapeer, C. M. and Leinus, J. and Martinsen, F. and Mauer, H. and N{\"u}then, I.}, edition = {Erscheinungsdatum: ca. 18.03.2024}, publisher = {Verlag Barbara Budrich}, language = {de} } @inproceedings{SchaefferHerrmannBoehm, author = {Schaeffer, Leon and Herrmann, David and B{\"o}hm, Valter}, title = {Preliminary considerations on the form-finding of a tensegrity joint to be used in dynamic orthoses}, series = {8th International Conference on Biomedical Engineering and Applications (ICBEA 2024), Tokio, 18-21. March 2024}, booktitle = {8th International Conference on Biomedical Engineering and Applications (ICBEA 2024), Tokio, 18-21. March 2024}, edition = {accepted paper}, publisher = {ACM}, language = {en} } @article{GradHonigDiemaretal., author = {Grad, Marius and Honig, Lars-Hauke and Diemar, Andreas and Flock, Dominik and Spieß, Lothar}, title = {Complex material analysis of a TiC coating produced by hot pressing with optical light microscopy, EDS, XRD, GDOES and EBSD}, series = {Surface \& Coatings Technology}, volume = {476}, journal = {Surface \& Coatings Technology}, publisher = {Elsevier}, doi = {10.1016/j.surfcoat.2023.130265}, abstract = {The present study investigates the interface between carbon steel and titanium samples annealed at different temperatures (𝜗1 = 800 ◦C and 𝜗2 = 1050 ◦C). In both cases, an observable layer forms at the interface, with its thickness increasing from t𝜗1= 2.75 ± 0.15 μm at 800 ◦C to t𝜗2= 8.86 ± 0.29 μm at 1050 ◦C. The layer's composition and thickness evolve with temperature. Analysis reveals approximately 40 at.-\% carbon concentration in the exterior region, indicating likely titanium carbide creation. X-ray diffraction identifies titanium carbide peaks, while microscopy and elemental mapping confirm compositional gradients at the interface. Electron Backscatter Diffraction (EBSD) shows a gradient in grain size near the TiC surface, reflecting TiC nucleation rates. XRD data detect both titanium carbide and titanium phases, with TiC becoming more prominent at 1050 ◦C. Rietveld analysis further confirms TiC formation. Notably, distinct diffraction patterns on the contact and rear sides suggest a Ti(C, O, N) presence. Depth profiles exhibit varying surface and depth carbon concentrations, attributed to temperature effects. The study successfully demonstrates TiC coating fabrication through hot pressing, wherein Ti(C, O, N) coatings arise from titanium's affinity for reacting with oxygen and nitrogen. This research contributes to the understanding of phase transformations and interfacial properties in titanium-carbon steel systems.}, language = {en} } @article{SalamaKouDawoudetal., author = {Salama, Amgad and Kou, Jisheng and Dawoud, Belal and Simonson, Carey}, title = {A modeling approach for capillary-driven flow of a wetting fluid in a rectangular open microchannel of arbitrary axisymmetric width profile}, series = {International Journal of Thermal Sciences}, volume = {195}, journal = {International Journal of Thermal Sciences}, publisher = {Elsevier}, issn = {1290-0729}, doi = {10.1016/j.ijthermalsci.2023.108622}, pages = {17}, abstract = {Microchips are intensively used in almost all nowadays electronic devices. With the continuous advancement of our technologies, they get smaller in size than ever before. They generate high-intensity heat loads that need to be transported effectively such that they may function properly. Heat pipes have proven to be very effective in transporting relatively large heat loads from miniature components. They are of seamless structure that involves a working fluid capable of evaporation and condensation at the working temperature of the electronic chips. The working fluid is derived to move from the condenser to the evaporator via multiple microgrooves using capillary forces. It is important that the condensate reaches the evaporator at a proper rate such that no dry-out or flooding occur. In this work, we are particularly interested in the case of capillary-driven flows in rectangular microchannels. A generalized model is developed that works for axe-symmetric rectangular channels of arbitrary, moderately varying width profiles. It also accounts for any contrast of viscosity between the liquid and the vapor under isothermal conditions. The model shows to reduce to the special case of imbibition in straight and uniform microchannels, for which comparisons with experimental and modeling works show an excellent match. Cases representing linearly and quadratically varying converging/diverging width profiles have been explored. It is found that the viscosity ratio has a significant influence on the rate at which the meniscus advances. The model also negates the common practice found in the literature of using the formula developed for imbibition rates in capillary tubes for rectangular microchannels by replacing the diameter of the tube with the hydraulic diameter. It is also found that the channel profile has an influential effect on the imbibition rates. For tapered microchannels, the capillary force increases along the channel length while it decreases for diverging ones. It is interestingly demonstrated that, for quadratically tapered microchannel, the speed of the meniscus increases towards the end of the microchannel compared with linearly varying microchannels. On the other hand, for diverging microchannels, the speed of the meniscus decreases due to the increase in the cross-sectional area. Computational fluid dynamics (CFD) analysis has been conducted to provide a framework for confirmation and verification for which very good match has been established, which builds confidence in the modeling approach.}, language = {en} }