TY - CHAP A1 - Milde, Benjamin A1 - Geislinger, Robert A1 - Lindt, Irina A1 - Baumann, Timo T1 - Open Source Automatic Lecture Subtitling T2 - Proceedings of Elektronische Sprachsignalverarbeitung (ESSV): Tagungsband der 32. Konferenz, Berlin, 3.-5. März 2021 N2 - 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. KW - automatische Spracherkennung KW - freie Software KW - Untertitelung Y1 - 2021 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:18-228-7-2523 UR - https://www.essv.de/pdf/2021_128_135.pdf?id=1109 SP - 128 EP - 135 PB - Förderverein Elektronische Sprachsignalverabeitung e.V. CY - Berlin, Germany ER - TY - CHAP A1 - Hussein, Hussein A1 - Meyer-Sickendiek, Burkhard A1 - Baumann, Timo ED - Birkholz, Peter ED - Stone, Simon T1 - How to identify elliptical poems within a digital corpus of auditory poetry T2 - Elektronische Sprachsignalverarbeitung 2019 (ESSV), Tagungsband der 30. Konferenz, Dresden, 3.-8. März 2019 N2 - 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. Y1 - 2019 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:18-228-7-2579 UR - http://www.essv.de/paper.php?id=88 SN - 978-3-959081-57-3 SP - 247 EP - 254 PB - TUDpress CY - Dresden, Germany ER - TY - CHAP A1 - Baumann, Timo A1 - Meyer-Sickendiek, Burkhard A1 - Hussein, Hussein T1 - How to Identify Speech When Translating Unpunctuated Poetry T2 - Proceedings of Elektronische Sprachsignalverarbeitung: Tagungsband der 31. Konferenz, Magdeburg, 4.-6. März 2020 N2 - 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. Y1 - 2020 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:18-228-7-2587 UR - http://www.essv.de/paper.php?id=452 SP - 165 EP - 172 PB - Förderverein Elektronische Sprachsignalverabeitung e.V. CY - Magdeburg, Germany ER - TY - CHAP A1 - Baumann, Timo A1 - Saboo, Ashutosh ED - Ehrmann, Maud T1 - Evaluating Heuristics for Audio-Visual Translation T2 - Proceedings of the Conference of Computational Humanities Research, (CHR2021): November 17-19, 2021, Amsterdam, The Netherlands N2 - 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. KW - ablation study KW - audiovisual translation KW - dubbing KW - lip synchrony KW - machine translation Y1 - 2021 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:18-228-7-2592 UR - http://ceur-ws.org/Vol-2989/short_paper46.pdf SP - 171 EP - 180 PB - CEUR Workshops CY - Amsterdam, the Netherlands ER - TY - CHAP A1 - Baumann, Timo T1 - Coordinating Speech Delivery to Gesture Progress for Deictic Expressions with Incremental Speech Synthesis T2 - 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 N2 - 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. KW - Incremental processing KW - speech synthesis KW - online adaptation KW - Inkrementelle Verarbeitung, KW - Sprachsynthese KW - Zeigegesten KW - Echtzeitadaptierung KW - Sprachverarbeitung Y1 - 2014 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:18-228-7-1991 UR - https://edoc.sub.uni-hamburg.de/informatik/volltexte/2014/199/pdf/timo_baumann_coordinating_speech_delivery.pdf ER - TY - GEN A1 - Meyer-Sickendiek, Burkhard A1 - Baumann, Timo A1 - Hussein, Hussein T1 - Requirements on the Punctuation Reconstruction for the Translation of Post-modern Poetry T2 - DHd 2020 ; Spielräume ; Digital Humanities zwischen Modellierung und Interpretation ; Konferenzabstracts ; Universität Paderborn 02. bis 06. März 2020 Y1 - 2020 SN - 978-3-945437-07-0 U6 - https://doi.org/10.5281/zenodo.4621722 PB - Universität Paderborn CY - Paderborn ER - TY - GEN A1 - Baumann, Timo ED - Devillers, Laurence ED - Kawahara, Tatsuya ED - Moore, Roger K. ED - Scheutz, Matthias T1 - Ubiquity of Computing and SLIVAR BT - Towards Effective and Ethical Interaction T2 - Spoken Language Interaction with Virtual Agents and Robots (SLIVAR): Towards Effective and Ethical Interaction KW - human-robot interaction KW - spoken language processing KW - virtual agents Y1 - 2020 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0030-drops-124009 VL - 10 PB - Schloss Dagstuhl ‐ Leibniz-Zentrum für Informatik CY - Dagstuhl, Germany ER - TY - GEN A1 - Meyer-Sickendiek, Burkhard A1 - Hussein, Hussein A1 - Baumann, Timo T1 - From Fluency To Disfluency: Ranking Prosodic Features Of Poetry By Using Neural Networks T2 - Proceedings of the International Conference on Digital Humanities (DH 2019), Utrecht, the Netherlands 9-12 July, 2019 Y1 - 2019 U6 - https://doi.org/10.34894/EGZNMI ER - TY - CHAP A1 - Windbühler, Anna A1 - Okkesim, Sükrü A1 - Christ, Olaf A1 - Mottaghi, Soheil A1 - Rastogi, Shavika A1 - Schmuker, Michael A1 - Baumann, Timo A1 - Hofmann, Ulrich G. T1 - Machine Learning Approaches to Classify Anatomical Regions in Rodent Brain from High Density Recordings T2 - 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2022): 11-15 July 2022, Glasgow, Scotland, United Kingdom N2 - 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. Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:898-opus4-35296 SP - 3530 EP - 3533 PB - IEEE ER - TY - GEN A1 - Tsai, Vivian A1 - Baumann, Timo A1 - Pecune, Florian A1 - Cassell, Justine T1 - Faster Responses are Better Responses: Introducing Incrementality into Sociable Virtual Personal Assistants Y1 - 2018 UR - https://colips.org/conferences/iwsds2018/wp/wp-content/uploads/2018/05/IWSDS-2018_paper_42_presentation.pdf ER - TY - GEN A1 - Paetzel, Maike A1 - Schlesinger, Philipp A1 - Pricop, Mircea A1 - Comaneci, Radu A1 - Baumann, Timo A1 - Menzel, Wolfgang T1 - Inkrementelle und zustandsbasierte Verarbeitung in einem hybriden Sprachdialogsystem BT - Postersession der Sektion Computerlinguistik Y1 - 2013 UR - https://www.researchgate.net/publication/236879516_Inkrementelle_und_zustandsbasierte_Verarbeitung_in_einem_hybriden_Sprachdialogsystem UR - https://www.timobaumann.de/work/uploads/Main/pentomino2013dgfsposter.pdf ER - TY - CHAP A1 - Baumann, Timo A1 - Paetzel, Maike A1 - Schlesinger, Philipp A1 - Menzel, Wolfgang T1 - Using Affordances to Shape the Interaction in a Hybrid Spoken Dialogue System T2 - Elektronische Sprachsignalverarbeitung 2013 : Tagungsband der 24. Konferenz, Bielefeld, 26. - 28.3.2013 ; [ESSV 2013] N2 - 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. Y1 - 2013 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:18-228-7-1836 UR - https://edoc.sub.uni-hamburg.de//informatik/volltexte/2013/183/ SN - 978-3-94431-03-4 SP - 12 EP - 19 PB - TUDpress ER - TY - BOOK A1 - Baumann, Timo T1 - Incremental Spoken Dialogue Processing: Architecture and Lower-level Components Y1 - 2012 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:361-25819101 SN - 9783848200221 N1 - Bielefeld, Univ., Diss., 2013 PB - Bielefeld University ER - TY - CHAP A1 - Schuler, Christian A1 - Nayak, Shravan A1 - Saha, Debjoy A1 - Baumann, Timo ED - Baumann, Timo T1 - Can We See Your Response Before You Speak? Exploring Linguistic Information Found in Inter-Utterance Pauses T2 - Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. März 2024 N2 - 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. Y1 - 2024 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:898-opus4-70949 SN - 978-3-95908-325-6 SP - 165 EP - 172 PB - TUDpress CY - Dresden ER - TY - CHAP A1 - Meyer-Sickendiek, Burkhard A1 - Hussein, Hussein A1 - Baumann, Timo ED - Berton, André ED - Haiber, Udo ED - Minker, Wolfgang T1 - Recognizing Modern Sound Poetry with LSTM Networks T2 - Proceedings of Elektronische Sprachsignalverarbeitung (ESSV) N2 - Our paper focuses on the computational analysis of “readout poetry” (german: Hördichtung) – 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 “Fümms bö wö tää zää 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. KW - Sprachverarbeitung Y1 - 2018 UR - http://www.essv.de/paper.php?id=407 SN - 978-3-959081-28-3 SP - 192 EP - 199 PB - TUDpress CY - Ulm, Germany ER - TY - CHAP A1 - Baumann, Timo A1 - Siegert, Ingo ED - Alt, Florian ED - Schneegass, Stefan ED - Hornecker, Eva T1 - Prosodic addressee-detection : ensuring privacy in always-on spoken dialog systems T2 - Tagungsband Mensch und Computer (MuC'20): 06.09.2020 - 09.09.2020, Magdeburg N2 - 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. KW - addressee detection KW - complexity-identical human-computer interaction KW - computational paralinguistics KW - fundamental frequency variation KW - recurrent neural network Y1 - 2020 SN - 9781450375405 U6 - https://doi.org/10.1145/3404983.3410021 SP - 195 EP - 198 PB - Association for Computing Machinery CY - New York, NY, United States ER - TY - JOUR A1 - Krüger, Norbert A1 - Fischer, Kerstin A1 - Manoonpong, Poramate A1 - Palinko, Oskar A1 - Bodenhagen, Leon A1 - Baumann, Timo A1 - Kjærum, Jens A1 - Rano, Ignacio A1 - Naik, Lakshadeep A1 - Juel, William Kristian A1 - Haarslev, Frederik A1 - Ignasov, Jevgeni A1 - Marchetti, Emanuela A1 - Langedijk, Rosalyn Melissa A1 - Kollakidou, Avgi A1 - Jeppesen, Kasper Camillus A1 - Heidtmann, Conny A1 - Dalgaard, Lars T1 - The SMOOTH-Robot: A Modular, Interactive Service Robot JF - Frontiers in Robotics and AI N2 - 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. KW - human–robot interaction KW - mobile robots KW - proactive control KW - service robots KW - socially aware navigation Y1 - 2021 U6 - https://doi.org/10.3389/frobt.2021.645639 VL - 8 PB - Frontiers ER - TY - JOUR A1 - Fischer, Kerstin A1 - Bodenhagen, Leon A1 - Krüger, Norbert A1 - Andersen, Morten Østergaard A1 - Baumann, Timo T1 - Trinvise og delte strategier for kontrol af velfærdsrobotter JF - Medicoteknik Y1 - 2015 UR - http://ipaper.ipapercms.dk/TechMedia/Medicoteknik/2015/1/?Page=11 VL - 2 IS - 1 SP - 11 EP - 13 PB - TechMedia ER - TY - CHAP A1 - Kousidis, Spyros A1 - Kennington, Casey A1 - Baumann, Timo A1 - Buschmeier, Hendrik A1 - Kopp, Stefan A1 - Schlangen, David T1 - Situationally Aware In-Car Information Presentation Using Incremental Speech Generation: Safer, and More Effective T2 - Proceedings of the EACL 2014 Workshop on Dialogue in Motion, Gothenburg, Sweden N2 - 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. KW - in-car information presentation KW - incremental speech generation KW - situation awareness Y1 - 2014 U6 - https://doi.org/10.3115/v1/W14-0212 SP - 68 EP - 72 PB - Association for Computational Linguistics ER - TY - CHAP A1 - Nayak, Shravan A1 - Schuler, Christian A1 - Saha, Debjoy A1 - Baumann, Timo ED - Tumuluri, Raj ED - Sebe, Nicu ED - Pingali, Gopal T1 - A Deep Dive Into Neural Synchrony Evaluation for Audio-visual Translation T2 - ICMI '22, Proceedings of the 2022 International Conference on Multimodal Interaction: November 7 - 11 2022, Bengaluru India N2 - 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). KW - audio-visual synchrony KW - speech-lip synchrony KW - dubbing Y1 - 2022 SN - 978-1-4503-9390-4 U6 - https://doi.org/10.1145/3536221.3556621 SP - 642 EP - 647 PB - Association for Computing Machinery CY - New York ER - TY - CHAP A1 - Melzer, Matthias A1 - Dünnweber, Jan A1 - Baumann, Timo T1 - Towards Smart Home Data Interpretation Using Analogies to Natural Language Processing T2 - 2022 IEEE International Conference on Smart Internet of Things: IEEE SmartIoT 2022, proceedings, 19-21 August 2022, Suzhou, China, hybrid conference (onsite and virtual) N2 - 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. KW - IoT KW - AI KW - NLP KW - Smart City Y1 - 2022 SN - 978-1-6654-7952-3 U6 - https://doi.org/10.1109/SmartIoT55134.2022.00020 SP - 65 EP - 71 PB - IEEE ER - TY - CHAP A1 - Hussein, Hussein A1 - Meyer-Sickendiek, Burkhard A1 - Baumann, Timo T1 - Automatic Detection of Enjambment in German Readout Poetry T2 - Proceedings of Speech Prosody, 2018, Poznán N2 - 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. KW - modern and postmodern poetry KW - free verse prosody KW - emphasized and unemphasized enjambment Y1 - 2018 U6 - https://doi.org/10.21437/SpeechProsody.2018-67 SP - 329 EP - 333 PB - ISCA ER - TY - CHAP A1 - Baumann, Timo A1 - Hussein, Hussein A1 - Meyer-Sickendiek, Burkhard T1 - Analysing the Focus of a Hierarchical Attention Network: the Importance of Enjambments When Classifying Post-modern Poetry T2 - Proceedings of Interspeech, 2018, Hyderabad N2 - After overcoming the traditional metrics, modern and postmodern poetry developed a large variety of ‘free verse prosodies’ that falls along a spectrum from a more fluent to a more disfluent and choppy style. We present a method, grounded in philological analysis and theories on cognitive (dis)fluency, to analyze this ‘free verse spectrum’ into six classes of poetic styles as well as to differentiate three types of poems with enjambments. We use a model for automatic prosodic analysis of spoken free verse poetry which uses deep hierarchical attention networks to integrate the source text and audio and predict the assigned class. We then analyze and fine-tune the model with a particular focus on enjambments and in two ways: we drill down on classification performance by analyzing whether the model focuses on similar traits of poems as humans would, specifically, whether it internally builds a notion of enjambment. We find that our model is similarly good as humans in finding enjambments; however, when we employ the model for classifying enjambment-dominated poem types, it does not pay particular attention to those lines. Adding enjambment labels to the training only marginally improves performance, indicating that all other lines are similarly informative for the model. KW - digital humanities KW - free verse poetry KW - prosodic analysis KW - enjambment detection KW - hierarchical attention network Y1 - 2018 U6 - https://doi.org/10.21437/Interspeech.2018-2533 SP - 2162 EP - 2166 ER - TY - CHAP A1 - Meyer-Sickendiek, Burkhard A1 - Hussein, Hussein A1 - Baumann, Timo ED - Burghardt, M. ED - Müller-Birn, C. T1 - Analysis and Classification of Prosodic Styles in Post-modern Spoken Poetry T2 - INF-DH 2018 Workshopband N2 - We present our research on computer-supported analysis of prosodic styles in post-modern poetry. Our project is unique in making use of both the written as well as the spoken form of the poem as read by the original author. In particular, we use speech and natural language processing technology to align speech and text and to perform textual analyses. We then explore, based on literary theory, the quantitative value of various types of features in differentiating various prosodic classes of post-modern poetry using machine-learning techniques. We contrast this feature-driven approach with a theoretically less informed neural networks-based approach and explore the relative strengths of both models, as well as how to integrate higher-level knowledge into the NN. In this paper, we give an overview of our project, our approach, and particularly focus on the challenges encountered and lessons learned in our interdisciplinary endeavour. The classification results of the rhythmical patterns (six classes) using NN-based approaches are better than by feature-based approaches. KW - modern and postmodern poetry KW - free verse prosody KW - rhythmical patters Y1 - 2018 U6 - https://doi.org/10.18420/infdh2018-09 PB - Gesellschaft für Informatik e.V ER -