@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} } @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} } @inproceedings{WindbuehlerOkkesimChristetal., author = {Windb{\"u}hler, Anna and Okkesim, S{\"u}kr{\"u} and Christ, Olaf and Mottaghi, Soheil and Rastogi, Shavika and Schmuker, Michael and Baumann, Timo and Hofmann, Ulrich G.}, title = {Machine Learning Approaches to Classify Anatomical Regions in Rodent Brain from High Density Recordings}, series = {44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2022): 11-15 July 2022, Glasgow, Scotland, United Kingdom}, booktitle = {44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2022): 11-15 July 2022, Glasgow, Scotland, United Kingdom}, publisher = {IEEE}, doi = {10.1109/EMBC48229.2022.9871702}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-35296}, pages = {3530 -- 3533}, abstract = {Identifying different functional regions during a brain surgery is a challenging task usually performed by highly specialized neurophysiologists. Progress in this field may be used to improve in situ brain navigation and will serve as an important building block to minimize the number of animals in preclinical brain research required by properly positioning implants intraoperatively. The study at hand aims to correlate recorded extracellular signals with the volume of origin by deep learning methods. Our work establishes connections between the position in the brain and recorded high-density neural signals. This was achieved by evaluating the performance of BLSTM, BGRU, QRNN and CNN neural network architectures on multisite electrophysiological data sets. All networks were able to successfully distinguish cortical and thalamic brain regions according to their respective neural signals. The BGRU provides the best results with an accuracy of 88.6 \% and demonstrates that this classification task might be solved in higher detail while minimizing complex preprocessing steps.}, 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} } @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} } @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{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{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} } @inproceedings{BaumannSiegert, author = {Baumann, Timo and Siegert, Ingo}, title = {Prosodic addressee-detection : ensuring privacy in always-on spoken dialog systems}, series = {Tagungsband Mensch und Computer (MuC'20): 06.09.2020 - 09.09.2020, Magdeburg}, booktitle = {Tagungsband Mensch und Computer (MuC'20): 06.09.2020 - 09.09.2020, Magdeburg}, editor = {Alt, Florian and Schneegass, Stefan and Hornecker, Eva}, publisher = {Association for Computing Machinery}, address = {New York, NY, United States}, isbn = {9781450375405}, doi = {10.1145/3404983.3410021}, pages = {195 -- 198}, abstract = {We analyze the addressee detection task for complexity-identical dialog for both human conversation and device-directed speech. Our recurrent neural model performs at least as good as humans, who have problems with this task, even native speakers, who profit from the relevant linguistic skills. We perform ablation experiments on the features used by our model and show that fundamental frequency variation is the single most relevant feature class. Therefore, we conclude that future systems can detect whether they are addressed based only on speech prosody which does not (or only to a very limited extent) reveal the content of conversations not intended for the system.}, language = {en} } @article{KruegerFischerManoonpongetal., author = {Kr{\"u}ger, Norbert and Fischer, Kerstin and Manoonpong, Poramate and Palinko, Oskar and Bodenhagen, Leon and Baumann, Timo and Kj{\ae}rum, Jens and Rano, Ignacio and Naik, Lakshadeep and Juel, William Kristian and Haarslev, Frederik and Ignasov, Jevgeni and Marchetti, Emanuela and Langedijk, Rosalyn Melissa and Kollakidou, Avgi and Jeppesen, Kasper Camillus and Heidtmann, Conny and Dalgaard, Lars}, title = {The SMOOTH-Robot: A Modular, Interactive Service Robot}, series = {Frontiers in Robotics and AI}, volume = {8}, journal = {Frontiers in Robotics and AI}, publisher = {Frontiers}, doi = {10.3389/frobt.2021.645639}, abstract = {The SMOOTH-robot is a mobile robot that-due to its modularity-combines a relatively low price with the possibility to be used for a large variety of tasks in a wide range of domains. In this article, we demonstrate the potential of the SMOOTH-robot through three use cases, two of which were performed in elderly care homes. The robot is designed so that it can either make itself ready or be quickly changed by staff to perform different tasks. We carefully considered important design parameters such as the appearance, intended and unintended interactions with users, and the technical complexity, in order to achieve high acceptability and a sufficient degree of utilization of the robot. Three demonstrated use cases indicate that such a robot could contribute to an improved work environment, having the potential to free resources of care staff which could be allocated to actual care-giving tasks. Moreover, the SMOOTH-robot can be used in many other domains, as we will also exemplify in this article.}, language = {en} } @article{FischerBodenhagenKruegeretal., author = {Fischer, Kerstin and Bodenhagen, Leon and Kr{\"u}ger, Norbert and Andersen, Morten {\O}stergaard and Baumann, Timo}, title = {Trinvise og delte strategier for kontrol af velf{\ae}rdsrobotter}, series = {Medicoteknik}, volume = {2}, journal = {Medicoteknik}, number = {1}, publisher = {TechMedia}, pages = {11 -- 13}, language = {da} } @inproceedings{KousidisKenningtonBaumannetal., author = {Kousidis, Spyros and Kennington, Casey and Baumann, Timo and Buschmeier, Hendrik and Kopp, Stefan and Schlangen, David}, title = {Situationally Aware In-Car Information Presentation Using Incremental Speech Generation: Safer, and More Effective}, series = {Proceedings of the EACL 2014 Workshop on Dialogue in Motion, Gothenburg, Sweden}, booktitle = {Proceedings of the EACL 2014 Workshop on Dialogue in Motion, Gothenburg, Sweden}, publisher = {Association for Computational Linguistics}, doi = {10.3115/v1/W14-0212}, pages = {68 -- 72}, abstract = {Holding non-co-located conversationswhile driving is dangerous (Horrey and- Wickens, 2006; Strayer et al., 2006), much more so than conversations with physically present, "situated" interlocutors (Drews et al., 2004). In-car dialogue systems typically resemble non-co-located conversations more, and share their negative impact (Strayer et al., 2013). We implemented and tested a simple strategy for making in-car dialogue systems aware of the driving situation, by giving them the capability to interrupt themselves when a dangerous situation is detected,and resume when over. We show that this improves both driving performance and recall of system-presented information, compared to a non-adaptive strategy.}, language = {en} } @inproceedings{NayakSchulerSahaetal., author = {Nayak, Shravan and Schuler, Christian and Saha, Debjoy and Baumann, Timo}, title = {A Deep Dive Into Neural Synchrony Evaluation for Audio-visual Translation}, series = {ICMI '22, Proceedings of the 2022 International Conference on Multimodal Interaction: November 7 - 11 2022, Bengaluru India}, booktitle = {ICMI '22, Proceedings of the 2022 International Conference on Multimodal Interaction: November 7 - 11 2022, Bengaluru India}, editor = {Tumuluri, Raj and Sebe, Nicu and Pingali, Gopal}, publisher = {Association for Computing Machinery}, address = {New York}, isbn = {978-1-4503-9390-4}, doi = {10.1145/3536221.3556621}, pages = {642 -- 647}, abstract = {We present a comprehensive analysis of the neural audio-visual synchrony evaluation tool SyncNet. We assess the agreement of SyncNet scores vis-a-vis human perception and whether we can use these as a reliable metric for evaluating audio-visual lip-synchrony in generation tasks with no ground truth reference audio-video pair. We further look into the underlying elements in audio and video which vitally affect synchrony using interpretable explanations from SyncNet predictions and analyse its susceptibility by introducing adversarial noise. SyncNet has been used in numerous papers on visually-grounded text-to-speech for scenarios such as dubbing. We focus on this scenario which features many local asynchronies (something that SyncNet isn't made for).}, language = {en} } @inproceedings{MelzerDuennweberBaumann, author = {Melzer, Matthias and D{\"u}nnweber, Jan and Baumann, Timo}, title = {Towards Smart Home Data Interpretation Using Analogies to Natural Language Processing}, series = {2022 IEEE International Conference on Smart Internet of Things: IEEE SmartIoT 2022, proceedings, 19-21 August 2022, Suzhou, China, hybrid conference (onsite and virtual)}, booktitle = {2022 IEEE International Conference on Smart Internet of Things: IEEE SmartIoT 2022, proceedings, 19-21 August 2022, Suzhou, China, hybrid conference (onsite and virtual)}, publisher = {IEEE}, isbn = {978-1-6654-7952-3}, doi = {10.1109/SmartIoT55134.2022.00020}, pages = {65 -- 71}, abstract = {Recent advances in the development of smart homes have led to the availability of a wide variety of devices providing a high level of convenience via gesture and speech control or fully automated operation. Many smart home appliances also address the aspects of safety and electricity savings by automatically powering themselves off after not being used for a while. However, many devices remain in a typical household that are not themselves "smart", or are not primarily electric (such as heating systems). We address the savings aspect by identifying processes involving the use of multiple devices in the electrical flow data, as captured by a smart meter in a modern household, rather than focusing on a single appliance. Therefore, we introduce a novel approach to usage pattern analysis based on the idea that a pattern of device usages as a result of a resident's 'routine' (such as making breakfast) can be interpreted similarly to a natural language 'sentence'; Natural Language Processing (NLP) algorithms can then be used for interpreting the residents' behavior. We introduce the notion of bag-of-devices (BoD), derived from the bag-of-words model used in document classification. In an experiment, we show how we use this model to infer predictions about the inhabitants from device usage, such as the resident leaving for the day or just to fetch the newspaper.}, language = {en} } @inproceedings{HusseinMeyerSickendiekBaumann, author = {Hussein, Hussein and Meyer-Sickendiek, Burkhard and Baumann, Timo}, title = {Automatic Detection of Enjambment in German Readout Poetry}, series = {Proceedings of Speech Prosody, 2018, Pozn{\´a}n}, booktitle = {Proceedings of Speech Prosody, 2018, Pozn{\´a}n}, publisher = {ISCA}, doi = {10.21437/SpeechProsody.2018-67}, pages = {329 -- 333}, abstract = {One of the most important patterns in ancient as well as modern poetry is the enjambment, the continuation of a sentence beyond the end of a line, couplet, or stanza. The paper reports first activities towards the development of a digital tool to analyze the accentuation of poetic enjambments in readout poetry. The aim in this contribution is to recognize two forms of enjambment (emphasized and unemphasized) in poems using audio and text data. We use data from lyrikline which is a major online portal for spoken poetry whereas poems are read aloud by the original authors. We identified by hermeneutical means based on literary analysis a total of 69 poems being characteristic for the use of enjambments in modern and postmodern German poetry and train classifiers to differentiate the emphasized/unemphasized ategorization. A remarkable result of our automated analyses (and to our knowledge the first data-driven analysis of this kind) is the identification of a cultural difference in the accentuation of enjambments: statistically speaking, poets from the former GDR tend to emphasize the enjambment, whereas poets from the FRG do not. We use features derived from speech-to-text alignment and statistical parsing information such as pause lengths, number of lines with verbs, and number of lines with punctuation. The best classification results, calculated by the F-measure, for the both types of enjambment (emphasized/unemphasized) is 0.69.}, language = {en} }