@article{Schiek, author = {Schiek, Roland}, title = {Excitation of nonlinear beams: from the linear Talbot effect through modulation instability to Akhmediev breathers}, series = {Optics express}, volume = {29}, journal = {Optics express}, number = {10}, publisher = {Optica Publishing Group}, address = {Washington, DC, USA}, doi = {10.1364/OE.425626}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-26049}, pages = {15830 -- 15851}, abstract = {The smooth transition between stable, Talbot-effect-dominated and modulationally unstable nonlinear optical beam propagation is described as the superposition of oscillating, growing and decaying eigenmodes of the common linearized theory of modulation instability. The saturation of the instability in form of breather maxima is embedded between eigenmode growth and decay. This explains well the changes of beam characteristics when the input intensity increases in experiments on modulation instability and breather excitation in spatial-spatial experimental platforms. An increased accuracy of instability gain measurements, a variety of interesting nonlinear beam scenarios and a more selective and well-directed breather excitation are demonstrated experimentally.}, language = {en} } @inproceedings{MildeGeislingerLindtetal., author = {Milde, Benjamin and Geislinger, Robert and Lindt, Irina and Baumann, Timo}, title = {Open Source Automatic Lecture Subtitling}, series = {Proceedings of Elektronische Sprachsignalverarbeitung (ESSV): Tagungsband der 32. Konferenz, Berlin, 3.-5. M{\"a}rz 2021}, booktitle = {Proceedings of Elektronische Sprachsignalverarbeitung (ESSV): Tagungsband der 32. Konferenz, Berlin, 3.-5. M{\"a}rz 2021}, publisher = {F{\"o}rderverein Elektronische Sprachsignalverabeitung e.V.}, address = {Berlin, Germany}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:18-228-7-2523}, pages = {128 -- 135}, abstract = {We present a fully automatic solution for German video subtitling, with a focus on lecture videos. We rely entirely on open source models and scripts for German ASR, automatic punctuation reconstruction and subtitle segmentation. All training scripts, 1000h of German speech training data, pre-trained models and the final subtitling program are publicly available. It can readily be integrated into lecture video platforms such as Lecture2Go. The automatically generated subtitles can also serve as a basis to make the video material more accessible (e.g. via search, keyword clouds, and the like) or for further manual revision, potentially helping in significantly speeding up manual work. A particular challenge that we observe in lectures are technical terms that are frequent in a particular lecture, but infrequent in a typical language model and that might be out of vocabulary for a general purpose ASR. We approach this challenge by extracting texts from accompanying lecture slides to adapt the language model of our TDNN-HMM based ASR system. We demonstrate the usability of the full system and its generated subtitles and evaluate on a dataset of manually transcribed lectures with an average of 26.3\% WER.}, language = {en} } @inproceedings{HusseinMeyerSickendiekBaumann, author = {Hussein, Hussein and Meyer-Sickendiek, Burkhard and Baumann, Timo}, title = {How to identify elliptical poems within a digital corpus of auditory poetry}, series = {Elektronische Sprachsignalverarbeitung 2019 (ESSV), Tagungsband der 30. Konferenz, Dresden, 3.-8. M{\"a}rz 2019}, booktitle = {Elektronische Sprachsignalverarbeitung 2019 (ESSV), Tagungsband der 30. Konferenz, Dresden, 3.-8. M{\"a}rz 2019}, editor = {Birkholz, Peter and Stone, Simon}, publisher = {TUDpress}, address = {Dresden, Germany}, isbn = {978-3-959081-57-3}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:18-228-7-2579}, pages = {247 -- 254}, abstract = {Ellipses denote the omission of one or more grammatically necessary phrases. In this paper, we will demonstrate how to identify such ellipses as a rhythmical pattern in modern and postmodern free verse poetry by using data from lyrikline which contain the corresponding audio recording of each poem as spoken by the original author. We present a feature engineering approach based on literary analysis as well as a neural networks based approach for the identification of ellipses within the lines of a poem. A contrast class to the ellipsis is defined from poems consisting of complete and correct sentences. The feature-based approach used features derived from a parser such as verb, comma, and sentence ending punctuation. The classifier of neural networks is trained on the line level to integrate the textual information, the spoken recitation, and the pause information between lines, and to integrate information across the lines within the poem. A statistic analysis of poet's gender showed that 65\% of all elliptical poems were written by female poets. The best results, calculated by the weighted F-measure, for the classification of ellipsis with the contrast class is 0.94 with the neural networks based approach. The best results for classification of elliptical lines is 0.62 with the feature-based approach.}, language = {en} } @inproceedings{BaumannMeyerSickendiekHussein, author = {Baumann, Timo and Meyer-Sickendiek, Burkhard and Hussein, Hussein}, title = {How to Identify Speech When Translating Unpunctuated Poetry}, series = {Proceedings of Elektronische Sprachsignalverarbeitung: Tagungsband der 31. Konferenz, Magdeburg, 4.-6. M{\"a}rz 2020}, booktitle = {Proceedings of Elektronische Sprachsignalverarbeitung: Tagungsband der 31. Konferenz, Magdeburg, 4.-6. M{\"a}rz 2020}, publisher = {F{\"o}rderverein Elektronische Sprachsignalverabeitung e.V.}, address = {Magdeburg, Germany}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:18-228-7-2587}, pages = {165 -- 172}, abstract = {A large proportion of (post)-modern poetry contains no or hardly any punctuation. In our contribution, we will investigate how well punctuation information can be recovered for postmodern poetry based on the information contained in the text and speech of free verse poems. We use the world's largest corpus of spoken (post-)modern poetry from our partner lyrikline which contains the corresponding audio recording of each poem as spoken by the original author and features translations for many of the poems. We identify lines that contain a phrase break in the middle of the poetic line, which may already be helpful for philological analysis on one hand, and identify the position of the break in the line on the other hand. We select those poetic lines that contain one or more punctuation characters that typically indicate a phrase break in poetry (.,;:!?/) somewhere in the middle (rather than only at the end of the line) as our target class. We train a neural network (bidirectional recurrent neural network (RNN) based on gated recurrent units (GRU) with attention) that combines audio and textual features to identify the punctuation with the goal of applying it to reconstruct them within a corpus of unpunctuated poems. Our results clearly indicate that speech is helpful for recovering the constituency structure of post-modern poetry that is partially obfuscated by missing punctuation.}, language = {en} } @inproceedings{BaumannSaboo, author = {Baumann, Timo and Saboo, Ashutosh}, title = {Evaluating Heuristics for Audio-Visual Translation}, series = {Proceedings of the Conference of Computational Humanities Research, (CHR2021): November 17-19, 2021, Amsterdam, The Netherlands}, booktitle = {Proceedings of the Conference of Computational Humanities Research, (CHR2021): November 17-19, 2021, Amsterdam, The Netherlands}, editor = {Ehrmann, Maud}, publisher = {CEUR Workshops}, address = {Amsterdam, the Netherlands}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:18-228-7-2592}, pages = {171 -- 180}, abstract = {Dubbing, i.e., the lip-synchronous translation and revoicing of audio-visual media into a target language from a different source language, is essential for the full-fledged reception of foreign audio-visual media, be it movies, instructional videos or short social media clips. In this paper, we objectify influences on the 'dubbability' of translations, i.e., how well a translation would be synchronously revoiceable to the lips on screen. We explore the value of traditional heuristics used in evaluating the qualitative aspects, in particular matching bilabial consonants and the jaw opening while producing vowels, and control for quantity, i.e., that translations are similar to the source in length. We perform an ablation study using an adversarial neural classifier which is trained to differentiate "true" dubbing translations from machine translations. While we are able to confirm the value of matching lip closure in dubbing, we find that the opening angle of the jaw as determined by the realized vowel may be less relevant than frequently considered in audio-visual translation.}, language = {en} } @inproceedings{Baumann, author = {Baumann, Timo}, title = {Coordinating Speech Delivery to Gesture Progress for Deictic Expressions with Incremental Speech Synthesis}, series = {Proceedings of the Timing in Human-Robot Interaction Workshop held in conjunction with the 9th ACM/IEEE International Conference on Human-Robot Interaction (HRI 2014), Bielefeld, 3. March 2014}, booktitle = {Proceedings of the Timing in Human-Robot Interaction Workshop held in conjunction with the 9th ACM/IEEE International Conference on Human-Robot Interaction (HRI 2014), Bielefeld, 3. March 2014}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:18-228-7-1991}, abstract = {This paper presents ongoing work in incremental speech synthesis that enables a system to adapt speech delivery to unforeseen changes in the timing of motor events (e. g. a robot actuator working faster or slower than anticipated) in order to improve the coordination of speech and gestures for deictic expressions.}, subject = {Sprachverarbeitung}, language = {en} } @unpublished{KratzerWestnerStrahringer, author = {Kratzer, Simon and Westner, Markus and Strahringer, Susanne}, title = {Four Decades of Chief Information Officer Research}, organization = {Association for Computing Machinery (ACM)}, doi = {10.1145/3614178.3614182}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-54208}, abstract = {Despite the relevance and maturity of the Chief Information Officer (CIO) research field, no studies exist that exhaustively summarize the current body of knowledge, focusing on the development of the field over its entire timespan. The paper at hand addresses this research gap and presents an exhaustive literature review on the CIO research field using main path analysis. We identify the central papers in CIO research and eight main research streams by quantitatively and qualitatively analyzing 466 papers. We find that established research streams, e.g., 'Evolving role of the CIO' and 'CIO hierarchical position and relationships' as well as recently emerging research streams, e.g., 'CIO as business enabler' and 'CIOs and IT security,' draw growing attention. Based on our findings, we develop promising further avenues for research in the CIO field.}, subject = {Informationsmanager}, language = {en} } @misc{MeyerSickendiekBaumannHussein, author = {Meyer-Sickendiek, Burkhard and Baumann, Timo and Hussein, Hussein}, title = {Requirements on the Punctuation Reconstruction for the Translation of Post-modern Poetry}, series = {DHd 2020 ; Spielr{\"a}ume ; Digital Humanities zwischen Modellierung und Interpretation ; Konferenzabstracts ; Universit{\"a}t Paderborn 02. bis 06. M{\"a}rz 2020}, journal = {DHd 2020 ; Spielr{\"a}ume ; Digital Humanities zwischen Modellierung und Interpretation ; Konferenzabstracts ; Universit{\"a}t Paderborn 02. bis 06. M{\"a}rz 2020}, publisher = {Universit{\"a}t Paderborn}, address = {Paderborn}, isbn = {978-3-945437-07-0}, doi = {10.5281/zenodo.4621722}, language = {en} } @misc{Baumann, author = {Baumann, Timo}, title = {Ubiquity of Computing and SLIVAR}, series = {Spoken Language Interaction with Virtual Agents and Robots (SLIVAR): Towards Effective and Ethical Interaction}, volume = {10}, journal = {Spoken Language Interaction with Virtual Agents and Robots (SLIVAR): Towards Effective and Ethical Interaction}, editor = {Devillers, Laurence and Kawahara, Tatsuya and Moore, Roger K. and Scheutz, Matthias}, publisher = {Schloss Dagstuhl - Leibniz-Zentrum f{\"u}r Informatik}, address = {Dagstuhl, Germany}, doi = {10.4230/DagRep.10.1.1}, url = {http://nbn-resolving.de/urn:nbn:de:0030-drops-124009}, pages = {16}, language = {en} } @misc{MeyerSickendiekHusseinBaumann, author = {Meyer-Sickendiek, Burkhard and Hussein, Hussein and Baumann, Timo}, title = {From Fluency To Disfluency: Ranking Prosodic Features Of Poetry By Using Neural Networks}, series = {Proceedings of the International Conference on Digital Humanities (DH 2019), Utrecht, the Netherlands 9-12 July, 2019}, journal = {Proceedings of the International Conference on Digital Humanities (DH 2019), Utrecht, the Netherlands 9-12 July, 2019}, doi = {10.34894/EGZNMI}, language = {en} } @misc{TsaiBaumannPecuneetal., author = {Tsai, Vivian and Baumann, Timo and Pecune, Florian and Cassell, Justine}, title = {Faster Responses are Better Responses: Introducing Incrementality into Sociable Virtual Personal Assistants}, language = {en} } @unpublished{BockWeiss, author = {Bock, Sebastian and Weiß, Martin Georg}, title = {Local Convergence of Adaptive Gradient Descent Optimizers}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-7546}, abstract = {Adaptive Moment Estimation (ADAM) is a very popular training algorithm for deep neural networks and belongs to the family of adaptive gradient descent optimizers. However to the best of the authors knowledge no complete convergence analysis exists for ADAM. The contribution of this paper is a method for the local convergence analysis in batch mode for a deterministic fixed training set, which gives necessary conditions for the hyperparameters of the ADAM algorithm. Due to the local nature of the arguments the objective function can be non-convex but must be at least twice continuously differentiable. Then we apply this procedure to other adaptive gradient descent algorithms and show for most of them local convergence with hyperparameter bounds.}, language = {en} } @inproceedings{WulfLindnerStrahringeretal., author = {Wulf, Frederik and Lindner, Tobias and Strahringer, Susanne and Westner, Markus}, title = {IaaS, PaaS, or SaaS? The Why of Cloud Computing Delivery Model Selection}, series = {Proceedings of the 54th Hawaii International Conference on System Sciences, 2021}, booktitle = {Proceedings of the 54th Hawaii International Conference on System Sciences, 2021}, isbn = {978-0-9981331-4-0}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-7913}, pages = {6285 -- 6294}, abstract = {Most large-scale organizations adopted Cloud Computing (CC) on a company level in recent years. Managers now face the challenge to appropriately implement CC "operationally", i.e., for information systems (ISs). We refer to this as post-adoption, addressing the extent of technology usage after adoption. Specifically, managers need to choose among the CC delivery models Infrastructure-as-a-Service (IaaS), Platform-as-a-Service (PaaS), and Software-asa-Service (SaaS). We differentiate the determinants of this post-adoption decision for IaaS, PaaS, and SaaS. Based on this analysis, we derive criteria that guide managers' delivery model selection: Adopt 1) IaaS for ISs requiring flexibility and reduced time to market, 2) PaaS to access specialized resources, and 3) SaaS to focus on core competencies. Moreover, we analyze the impact on the CC strategy and postulate them as recommendations: I) acknowledge the interplay between governance and time-to-market, II) realize cost savings on company level, and III) consider strategically important ISs for CC.}, language = {en} } @misc{Hipp, author = {Hipp, Susanne}, title = {Small antennas in huge environments - simulation using hybrid methods}, series = {Workshop des ITG-Fachausschuss HF1: Innovative Beamforming Antennas}, journal = {Workshop des ITG-Fachausschuss HF1: Innovative Beamforming Antennas}, language = {en} } @misc{PaetzelSchlesingerPricopetal., author = {Paetzel, Maike and Schlesinger, Philipp and Pricop, Mircea and Comaneci, Radu and Baumann, Timo and Menzel, Wolfgang}, title = {Inkrementelle und zustandsbasierte Verarbeitung in einem hybriden Sprachdialogsystem}, language = {en} } @misc{HobelsbergerMottokDumke, author = {Hobelsberger, Martin and Mottok, J{\"u}rgen and Dumke, Reiner}, title = {A model based safety analysis approach for embedded system architectures}, series = {Tag der Technik 2008}, journal = {Tag der Technik 2008}, language = {en} } @misc{Hipp, author = {Hipp, Susanne}, title = {Designing steerable antenna arrays using simulation}, series = {GeMIC 2020}, journal = {GeMIC 2020}, abstract = {Antenna arrays are one possibility to design a steerable antenna. Designing an antenna array is a challenging task, where simulation can help to reduce the design complexity. Simulating a complete array can be computational expensive, therefore designing the array is often broken in several task. The first goal is to design and optimize a single antenna element followed by an optimization of this antenna element while considering the vicinity of further equal elements. A unit cell approach is a feasible and easy way to accomplish this task. This approach already considers parameter such as active element pattern and radiation pattern angles. As soon as the unit cell optimization, emulating an infinite array, is finished, the real array with a finite size is simulated, especially considering edge elements and parameters such as excitation patterns or active and passive elements. Due to the high simulation effort at this stage optimization should be kept to a minimum and high performance computing might be required. Finally, a feeding network and different excitations for various beam patterns can be investigated using combined methods to reduce the simulation effort.}, subject = {Antennengruppe}, language = {en} } @misc{RennerPozzobon, author = {Renner, Sebastian and Pozzobon, Enrico}, title = {SIM SIMulator}, series = {IT Security Conference Troopers19, 2019, Heidelberg, Germany}, journal = {IT Security Conference Troopers19, 2019, Heidelberg, Germany}, abstract = {Der Vortrag pr{\"a}sentierte ein Tool, das die Simulation einer SIM-Karte durch einen Standard-Mikrocontroller erm{\"o}glicht. Mit diesem T{\"a}uschungsman{\"o}ver kann die Authentifizierung des 3G-Mobilfunkstandards seitens der SIM-Karte umgangen werden. Tritt zus{\"a}tzliche Hardware hinzu, die eine 3G-Basisstation vort{\"a}uscht, l{\"a}sst sich eine Man-in-the-Middle-Attacke im 3G-Netz durchf{\"u}hren. In diesem Szenario ist es m{\"o}glich, die sensiblen Kommunikationsdaten, also den gesamten Datenverkehr beispielsweise zwischen einem Pkw und den Backend-Servern des Herstellers, auszulesen und zu untersuchen. Zudem eignet sich das Tool zum Pentesten von Modems oder SIM- beziehungsweise Smartcard-Applikationen. Der komplette Aufbau des sogenannten SIMulators ist als Open-Source-Software frei verf{\"u}gbar und auf GitHub abrufbar.}, language = {en} } @techreport{Steffens, author = {Steffens, Oliver}, title = {Report on a Vernier (Nonius Rule) for Non-Linear Scales}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-58926}, pages = {7}, abstract = {The vernier or nonius (in other languages) goes back to a measuring tool used in navigation and astronomy named after its inventor Pedro Nunes (1502-1578; Latin: Petrus Nonius), a Portuguese mathematician and navigator. The nonius was created in 1542 to take finer measurements on circular instruments such as the astrolabe. In 1631 the French mathematician Pierre Vernier (1580-1637) adapted and simplified the system which was later denoted "vernier". We present a method to construct a vernier-like scale for logarithmic scales (as used for typical slide rules), which results in variable tick spacings. The idea is to put the non-linear scale on a spiral. The method can be applied to any non-linear scale, not only logarithmic scales.}, language = {en} } @techreport{Steffens, type = {Working Paper}, author = {Steffens, Oliver}, title = {A Perpetual Calendar Slide Rule}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-58935}, abstract = {We present a method and demonstrate the construction of an analog (mechanical/graphical) perpetual calendar device for the Gregorian calendar system. It allows to calculate the weekdays of a day in any year (and vice versa).}, language = {en} } @inproceedings{BaumannPaetzelSchlesingeretal., author = {Baumann, Timo and Paetzel, Maike and Schlesinger, Philipp and Menzel, Wolfgang}, title = {Using Affordances to Shape the Interaction in a Hybrid Spoken Dialogue System}, series = {Elektronische Sprachsignalverarbeitung 2013 : Tagungsband der 24. Konferenz, Bielefeld, 26. - 28.3.2013 ; [ESSV 2013]}, booktitle = {Elektronische Sprachsignalverarbeitung 2013 : Tagungsband der 24. Konferenz, Bielefeld, 26. - 28.3.2013 ; [ESSV 2013]}, publisher = {TUDpress}, isbn = {978-3-94431-03-4}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:18-228-7-1836}, pages = {12 -- 19}, abstract = {Affordances manifest possibilities of interaction with a spoken dialogsystem. For example, the act of asking a question affords to the recipient thepossibility of answering. In the system we present, the observable act of maneuveringaffords the possibility of controlling a motion. Our system thus uses the affordanceprinciple to shape the interaction: to trigger the usage of instructions that are easyto understand and process, the system gives immediate visual feedback to afforduser commands that can then be reacted upon. This tightening of the interactionloop requires an incremental processing paradigm to allow fast reactions and to beable to alter ongoing system actions. Our system is a hybrid of incremental andnon-incremental processing components, combining conventional, state graph-basedprocessing, which has the advantage of widely available toolkits and well-understooddialog management, with incremental dialog processing which allows for the tightfeedback loop that provides for quick reactions. We tested our approach in a smalluser study and found that users used simpler and setting-independent commandsmore often and were more efficient when faced with the affordance-based version ofour system.}, language = {en} } @book{Baumann, author = {Baumann, Timo}, title = {Incremental Spoken Dialogue Processing: Architecture and Lower-level Components}, publisher = {Bielefeld University}, isbn = {9783848200221}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:361-25819101}, pages = {176}, language = {en} } @inproceedings{BrosigWestnerStrahringer, author = {Brosig, Christoph and Westner, Markus and Strahringer, Susanne}, title = {Linking IT assets and competitive advantage - IT capabilities of servitized business models}, series = {34th Bled eConference Digital Support from Crisis to Progressive Change: June 27 - 30, 2021, Online: Conference Proceedings}, booktitle = {34th Bled eConference Digital Support from Crisis to Progressive Change: June 27 - 30, 2021, Online: Conference Proceedings}, editor = {Borštnar, Mirjana Kljajić}, isbn = {978-961-286-485-9}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-20158}, pages = {111 -- 123}, abstract = {This paper connects research from business model innovation and information systems by exploring critical IT capabilities for servitized business models. The adoption of servitized business models is a major business model innovation strategy. At the same time, digitalization drives the evolution of IT capabilities at these business models. Scholars argue that it remains unclear how IT capabilities enable servitized business models to build a competitive advantage by achieving cost advantages or differentiation. This paper explores IT capabilities that enable building a competitive advantage for servitized business models based on a qualitative analysis of multiple published case studies. The authors identify configurations of IT capabilities among servitized business models. The findings contribute to servitization research by exploring IT capabilities and how they are combined among servitized business models. The insights help practitioners deploy digital technologies and IT assets effectively as building blocks of IT capabilities to advance their servitized business model.}, subject = {Gesch{\"a}ftsmodell}, language = {en} } @unpublished{Weiss, author = {Weiß, Martin Georg}, title = {Optimization of Cartesian Tasks with Configuration Selection}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-20176}, abstract = {A basic task in the design of an industrial robot application is the relative placement of robot and workpiece. Process points are defined in Cartesian coordinates relative to the workpiece coordinate system, and the workpiece has to be located such that the robot can reach all points. Finding such a location is still an iterative procedure based on the developers' intuition. One difficulty is the choice of one of the several solutions of the backward transform of a typical 6R robot. We present a novel algorithm that simultaneously optimizes the workpiece location and the robot configuration at all process points using higher order optimization algorithms. A key ingredient is the extension of the robot with a virtual prismatic axis. The practical feasibility of the approach is shown with an example using a commercial industrial robot.}, subject = {Intralogistik}, 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{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{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{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{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{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{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{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{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} } @incollection{KinoshitaDelcroixGannotetal., author = {Kinoshita, Keisuke and Delcroix, Marc and Gannot, Sharon and Habets, Emanu{\"e}l A. P. and Haeb-Umbach, Reinhold and Kellermann, Walter and Leutnant, Volker and Maas, Roland and Nakatani, Tomohiro and Raj, Bhiksha and Sehr, Armin and Yoshioka, Takuya}, title = {The REVERB Challenge: A Benchmark Task for Reverberation-Robust ASR Techniques}, series = {New Era for Robust Speech Recognition}, volume = {27}, booktitle = {New Era for Robust Speech Recognition}, editor = {Watanabe, Shinji and Delcroix, Marc and Metze, Florian and Hershey, John R.}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-64679-4}, doi = {10.1007/978-3-319-64680-0_15}, pages = {345 -- 354}, abstract = {The REVERB challenge is a benchmark task designed to evaluate reverberation-robust automatic speech recognition techniques under various conditions. A particular novelty of the REVERB challenge database is that it comprises both real reverberant speech recordings and simulated reverberant speech, both of which include tasks to evaluate techniques for 1-, 2-, and 8-microphone situations. In this chapter, we describe the problem of reverberation and characteristics of the REVERB challenge data, and finally briefly introduce some results and findings useful for reverberant speech processing in the current deep-neural-network era.}, 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{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{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{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} } @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{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} } @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} } @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{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{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{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{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{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{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{WiesmaierLippertKaratsiolisetal., author = {Wiesmaier, Alexander and Lippert, Markus and Karatsiolis, Vangelis and Raptis, Georgios and Buchmann, Johannes}, title = {An Evaluated Certification Services System for the German National Root CA - Legally Binding and Trustworthy Transactions in E-Business and E-Government}, series = {Proceedings of The 2005 International Conference on E-Business, Enterprise Information Systems, E-Government, and Outsourcing, EEE 2005, Las Vegas, Nevada, USA, June 20-23, 2005}, booktitle = {Proceedings of The 2005 International Conference on E-Business, Enterprise Information Systems, E-Government, and Outsourcing, EEE 2005, Las Vegas, Nevada, USA, June 20-23, 2005}, publisher = {CSREA Press}, isbn = {1-932415-76-9}, pages = {103 -- 108}, language = {en} } @inproceedings{MeyerSickendiekHusseinBaumann, author = {Meyer-Sickendiek, Burkhard and Hussein, Hussein and Baumann, Timo}, title = {Recognizing Modern Sound Poetry with LSTM Networks}, series = {Proceedings of Elektronische Sprachsignalverarbeitung (ESSV)}, booktitle = {Proceedings of Elektronische Sprachsignalverarbeitung (ESSV)}, editor = {Berton, Andr{\´e} and Haiber, Udo and Minker, Wolfgang}, publisher = {TUDpress}, address = {Ulm, Germany}, isbn = {978-3-959081-28-3}, pages = {192 -- 199}, abstract = {Our paper focuses on the computational analysis of "readout poetry" (german: H{\"o}rdichtung) - recordings of poets reading their own work - with regards to the most important type of this genre, the modern "sound poetry" (german: Lautdichtung). Whereas "readout poetry" often uses normal words and sentences, the "sound poetry", developed by dadaistic poets like Hugo Ball and Kurt Schwitters or concrete poets like Ernst Jandl, Oskar Pastior, or Bob Cobbing, combines the "microparticles of the human voice" like the segments in Ernst Jandls sound poem "schtzngrmm" ("schtzngrmm / schtzngrmm / tttt / tttt / grrrmmmmm / tttt / sch / tzngrmm"). Within the genre of sound poetry, there are two main forms: The lettristic and the syllabic decomposition. A short anecdote will explain this difference: The dadaist Raoul Hausmann developed the lettristic sound poetry in his early dadaistic poem "fmsbw" from 1918. This is said to have inspired his successor Schwitters, whose famous "Ursonate" [The Sonata in Primal Speech] begins with the words "F{\"u}mms b{\"o} w{\"o} t{\"a}{\"a} z{\"a}{\"a} Uu". With the "Ursonate", Schwitters developed a syllabic variation of the lettristic poems of Hausmann. The paper shows how to train a bidirectional LSTM network in order to differ between these "dadaistic" sound poems and the "normal" read out poems. In a further step, we will also show how to distinguish between the lettristic and the syllabic decomposition. Based on a bidirectional LSTM network that reads encodings of the character sequence in the poem and uses the output of each directional layer, we identify poems of the sound poetry genre and differentiate between its two types of compositions. The classification results of sound poetry vs. other poetry as well as lettristic vs. syllabic decomposition are with a high performance, yielding a f-scores of 0.86 and 0.84, respectively.}, subject = {Sprachverarbeitung}, language = {en} }