@inproceedings{KenningtonKousidisBaumannetal., author = {Kennington, Casey and Kousidis, Spyros and Baumann, Timo and Buschmeier, Hendrik and Kopp, Stefan and Schlangen, David}, title = {Better Driving and Recall When In-car Information Presentation Uses Situationally-Aware Incremental Speech Output Generation}, series = {Proceedings of the 6th International Conference on Automotive User Interfaces and Interactive Vehicular Applications, AutomotiveUI '14, Seattle WA, USA, September 17 - 19, 2014}, booktitle = {Proceedings of the 6th International Conference on Automotive User Interfaces and Interactive Vehicular Applications, AutomotiveUI '14, Seattle WA, USA, September 17 - 19, 2014}, editor = {Miller, Erika and Wu, Yuqing}, publisher = {ACM}, address = {New York, NY}, doi = {10.1145/2667317.2667332}, pages = {1 -- 7}, abstract = {It is established that driver distraction is the result of sharing cognitive resources between the primary task (driving) and any other secondary task. In the case of holding conversations, a human passenger who is aware of the driving conditions can choose to interrupt his speech in situations potentially requiring more attention from the driver, but in-car information systems typically do not exhibit such sensitivity. We have designed and tested such a system in a driving simulation environment. Unlike other systems, our system delivers information via speech (calendar entries with scheduled meetings) but is able to react to signals from the environment to interrupt when the driver needs to be fully attentive to the driving task and subsequently resume its delivery. Distraction is measured by a secondary short-term memory task. In both tasks, drivers perform significantly worse when the system does not adapt its speech, while they perform equally well to control conditions (no concurrent task) when the system intelligently interrupts and resumes.}, language = {en} } @inproceedings{Baumann, author = {Baumann, Timo}, title = {Partial Representations Improve the Prosody of Incremental Speech Synthesis}, series = {Interspeech 2014, Singapore, 14-18 September 2014}, booktitle = {Interspeech 2014, Singapore, 14-18 September 2014}, doi = {10.21437/Interspeech.2014-199}, pages = {2932 -- 2936}, abstract = {When humans speak, they do not plan their full utterance inall detail before beginning to speak, nor do they speak piece-by-piece and ignoring their full message - instead humans usepartial representations in which they fill in the missing partsas the utterance unfolds. Incremental speech synthesizers, incontrast, have not yet made use of partial representations and theinformation contained there-in.We analyze the quality of prosodic parameter assignments(pitch and duration) generated from partial utterance specifi-cations (substituting defaults for missing features) in order todetermine the requirements that symbolic incremental prosodymodelling should meet. We find that broader, higher-level infor-mation helps to improve prosody even if lower-level informationabout the near future is yet unavailable. Furthermore, we findthat symbolic phrase-level or utterance-level information is mosthelpful towards the end of the phrase or utterance, respectively,that is, when this information is becoming available even in theincremental case. Thus, the negative impact of incremental pro-cessing can be minimized by using partial representations thatare filled in incrementally.}, language = {en} } @inproceedings{KousidisKenningtonBaumannetal., author = {Kousidis, Spyros and Kennington, Casey and Baumann, Timo and Buschmeier, Hendrik and Kopp, Stefan and Schlangen, David}, title = {A Multimodal In-Car Dialogue System That Tracks The Driver's Attention}, series = {Proceedings of the 16th International Conference on Multimodal Interaction, ICMI '14, November 12 - 16 2014, Istanbul}, booktitle = {Proceedings of the 16th International Conference on Multimodal Interaction, ICMI '14, November 12 - 16 2014, Istanbul}, editor = {Ali Salah, Albert}, publisher = {ACM}, address = {New York, NY}, isbn = {9781450328852}, doi = {10.1145/2663204.2663244}, pages = {26 -- 33}, abstract = {When a passenger speaks to a driver, he or she is co-located with the driver, is generally aware of the situation, and can stop speaking to allow the driver to focus on the driving task. In-car dialogue systems ignore these important aspects, making them more distracting than even cell-phone conversations. We developed and tested a "situationally-aware" dialogue system that can interrupt its speech when a situation which requires more attention from the driver is detected, and can resume when driving conditions return to normal. Furthermore, our system allows driver-controlled resumption of interrupted speech via verbal or visual cues (head nods). Over two experiments, we found that the situationally-aware spoken dialogue system improves driving performance and attention to the speech content, while driver-controlled speech resumption does not hinder performance in either of these two tasks}, language = {en} } @inproceedings{BaumannLindner, author = {Baumann, Timo and Lindner, Felix}, title = {Incremental Speech Production for Polite and Natural Personal-Space Intrusion}, series = {Social robotics : 7th International Conference, ICSR 2015, Paris, France, October 26-30, 2015, Proceedings}, booktitle = {Social robotics : 7th International Conference, ICSR 2015, Paris, France, October 26-30, 2015, Proceedings}, editor = {Tapus, Adriana and Andr{\´e}, Elisabeth and Martin, Jean-Claude}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-25553-8}, doi = {10.1007/978-3-319-25554-5_8}, pages = {72 -- 82}, abstract = {We propose to use a model of personal space to initiate communication while passing a human thereby acknowledging that humans are not just a special kind of obstacle to be avoided but potential interaction partners. As a simple form of interaction, our system communicates an apology while closely passing a human. To this end, we present a software architecture that integrates a social-spaces knowledge base and a component for incremental speech production. Incrementality ensures that the robot's utterance can be adapted to fit the developing situation in a natural way. Observer ratings show that personal-space intrusion is perceived as both natural and polite if the robot has the capability to utter and adapt an apology in an incremental way whereas it is perceived as unfriendly if the robot intrudes personal space without saying anything. Moreover, the robot is perceived as less natural if it does not adapt.}, language = {en} } @inproceedings{BaumannKenningtonHoughetal., author = {Baumann, Timo and Kennington, Casey and Hough, Julian and Schlangen, David}, title = {Recognising Conversational Speech: What an Incremental ASR Should Do for a Dialogue System and How to Get There}, series = {Proceedings of the International Workshop Series on Spoken Dialogue Systems Technology (IWSDS) 2016}, booktitle = {Proceedings of the International Workshop Series on Spoken Dialogue Systems Technology (IWSDS) 2016}, abstract = {Automatic speech recognition (ASR) is not only becoming increasingly accurate, but also increasingly adapted for producing timely, incremental output. However, overall accuracy and timeliness alone are insufficient when it comes to interactive dialogue systems which require stability in the output and responsivity to the utterance as it is unfolding. Furthermore, for a dialogue system to deal with phenomena such as disfluencies, to achieve deep understanding of user utterances these should be preserved or marked up for use by downstream components, such as language understanding, rather than be filtered out. Similarly, word timing can be informative for analyzing deictic expressions in a situated environment and should be available for analysis. Here we investigate the overall accuracy and incremental performance of three widely used systems and discuss their suitability for the aforementioned perspectives. From the differing performance along these measures we provide a picture of the requirements for incremental ASR in dialogue systems and describe freely available tools for using and evaluating incremental ASR.}, language = {en} } @inproceedings{BaumannLindner, author = {Baumann, Timo and Lindner, Felix}, title = {Towards a Social Robot that Incrementally Justifies Personal-Space Intrusion}, series = {Proceedings of the Workshop Towards a Framework for Joint Action 2015}, booktitle = {Proceedings of the Workshop Towards a Framework for Joint Action 2015}, abstract = {Robots should appropriately give reasons for their actions when these actions affect a human's action or goal space. Communicating reasons may help the human understand the robot's intents and may initiate joint action, i. e., accepting the robot's goals and cooperating on the robot's actions. However, to be efficient, the communication of reasons should be limited to the necessary rather than to completeness, conforming to the Gricean Maxim of Quantity. Furthermore, what is necessary only becomes apparent as the situation evolves and hence, for seamless interaction, ongoing utterances must be adapted as they happen. We present a system that flexibly gives reasons in a reduced setting in which the robot needs to intrude a human's personal space in order to reach its goal.}, language = {en} } @inproceedings{PougetHueberBaillyetal., author = {Pouget, Ma{\"e}l and Hueber, Thomas and Bailly, G{\´e}rard and Baumann, Timo}, title = {HMM training strategy for incremental speech synthesis}, series = {Interspeech 2015, Dresden, Germany, 6-10 September 2015}, booktitle = {Interspeech 2015, Dresden, Germany, 6-10 September 2015}, publisher = {ISCA}, doi = {10.21437/Interspeech.2015-304}, pages = {1201 -- 1205}, abstract = {Incremental speech synthesis aims at delivering the synthetic voice while the sentence is still being typed. One of the main challenges is the online estimation of the target prosody from a partial knowledge of the sentence's syntactic structure. In the context of HMM-based speech synthesis, this typically results in missing segmental and suprasegmental features, which describe the linguistic context of each phoneme. This study describes a voice training procedure which integrates explicitly a potential uncertainty on some contextual features. The proposed technique is compared to a baseline approach (previously published), which consists in substituting a missing contextual feature by a default value calculated on the training set. Both techniques were implemented in a HMM-based Text-To-Speech system for French, and compared using objective and perceptual measurements. Experimental results show that the proposed strategy outperforms the baseline technique for this language.}, language = {en} } @inproceedings{Baumann, author = {Baumann, Timo}, title = {Decision Tree Usage for Incremental Parametric Speech Synthesis}, series = {Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2014, 4-9 May 2014, Florence, Italy}, booktitle = {Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2014, 4-9 May 2014, Florence, Italy}, publisher = {IEEE}, doi = {10.1109/ICASSP.2014.6854316}, pages = {3847 -- 3851}, abstract = {Human speakers plan and deliver their utterances incrementally, piece-by-piece, and it is obvious that their choice regarding phonetic details (and the details' peculiarities) is rarely determined by globally optimal solutions. In contrast, parametric speech synthesizers use a full-utterance context when optimizing vocoding parameters and when determing HMM states. Apart from being cognitively implausible, this impedes incremental use-cases, where the future context is often at least partially unavailable. This paper investigates the `locality' of features in parametric speech synthesis voices and takes some missing steps towards better HMM state selection and prosody modelling for incremental speech synthesis.}, language = {en} } @inproceedings{BaumannBangaloreHirschberg, author = {Baumann, Timo and Bangalore, Srinivas and Hirschberg, Julia}, title = {Towards Simultaneous Interpreting: The Timing of Incremental Machine Translation and Speech Synthesis}, series = {Proceedings of the 11th International Workshop on Spoken Language Translation. Papers. Lake Tahoe, December 4th and 5th, 2014}, booktitle = {Proceedings of the 11th International Workshop on Spoken Language Translation. Papers. Lake Tahoe, December 4th and 5th, 2014}, editor = {Federico, Marcello and St{\"u}ker, Sebastian and Yvon, Fran{\c{c}}ois}, pages = {163 -- 168}, abstract = {In simultaneous interpreting, human experts incrementally construct and extend partial hypotheses about the source speaker's message, and start to verbalize a corresponding message in the target language, based on a partial translation - which may have to be corrected occasionally. They commence the target utterance in the hope that they will be able to finish understanding the source speaker's message and determine its translation in time for the unfolding delivery. Of course, both incremental understanding and translation by humans can be garden-pathed, although experts are able to optimize their delivery so as to balance the goals of minimal latency, translation quality and high speech fluency with few corrections. We investigate the temporal properties of both translation input and output to evaluate the tradeoff between low latency and translation quality. In addition, we estimate the improvements that can be gained with a tempo-elastic speech synthesizer.}, language = {en} } @article{MeyerSickendiekHusseinBaumann, author = {Meyer-Sickendiek, Burkhard and Hussein, Hussein and Baumann, Timo}, title = {Towards the Creation of a Poetry Translation Mapping System}, series = {Archives of Data Science, Series A}, volume = {5}, journal = {Archives of Data Science, Series A}, number = {1}, publisher = {Towards the Creation of a Poetry Translation Mapping System}, issn = {2363-9881}, doi = {10.5445/KSP/1000087327/21}, pages = {1 -- 15}, abstract = {The translation of poetry is a complex, multifaceted challenge: the translated text should communicate the same meaning, similar metaphoric expressions, and also match the style and prosody of the original poem. Research on machine poetry translation is existing since 2010, but for four reasons it is still rather insufficient: 1. The few approaches existing completely lack any knowledge about current developments in both lyric theory and translation theory. 2. They are based on very small datasets. 3. They mostly ignored the neural learning approach that superseded the long-standing dominance of phrase-based approaches within machine translation. 4. They have no concept concerning the pragmatic function of their research and the resulting tools. Our paper describes how to improve the existing research and technology for poetry translations in exactly these four points. With regards to 1) we will describe the "Poetics of Translation". With regards to 2) we will introduce the Worlds largest corpus for poetry translations from lyrikline. With regards to 3) we will describe first steps towards a neural machine translation of poetry. With regards to 4) we will describe first steps towards the development of a poetry translation mapping system.}, language = {en} } @misc{WardBaumannKarkhedkaretal., author = {Ward, Nigel and Baumann, Timo and Karkhedkar, Shreyas and Novick, David}, title = {Dynamic control of voice codec data rate}, abstract = {A method, system, and computer-usable non-transitory storage device for dynamic voice codec adaptation are disclosed. The voice codec adapts in real time to devote more bits to audio quality when it is most needed, and fewer bits to less important parts of utterances are disclosed. Dialog knowledge is utilized for compression opportunities to adjust the bitrate moment-by-moment, based on the inferred value of each frame. Frame importance and appropriate transmission fidelity is predicted based on prosodic features and models of dialog dynamics. This technique provides the same communications quality with less spectrum needs, fewer antennas, and less battery drain.}, language = {en} } @article{BrosigStrahringerWestner, author = {Brosig, Christoph and Strahringer, Susanne and Westner, Markus}, title = {From selling machinery to hybrid offerings}, series = {International Journal of Information Systems and Project Management}, volume = {10}, journal = {International Journal of Information Systems and Project Management}, number = {3}, publisher = {SciKA}, issn = {2182-7788}, doi = {10.12821/ijispm100301}, pages = {5 -- 27}, abstract = {The transition towards services has been imperative for manufacturing firms for years. The change from a productoriented to a more service-dominant business model affects the organizational structure of firms. However, literature provides limited insights into how manufacturing firms organize themselves in this transition. Even though digital technologies are critical for the transition, it is unclear how to orchestrate digital and traditional Information Technology (IT) resources in manufacturing firms accordingly. We analyze the case of a typical manufacturing firm that has adjusted its structure to reorganize for solution offerings based on product, service, and digital components. Our results describe a hybrid organizational structure that splits front- and back-end units. The back-end units are split along solution components. Digital IT resources are internalized and governed decentrally, with traditional IT resources being outsourced and steered centrally. Our findings contribute to digital servitization research by clarifying the overarching as well as the digital and traditional IT-related organization for manufacturing firms.}, language = {en} } @inproceedings{SchindlerSkornia, author = {Schindler, Timo and Skornia, Christoph}, title = {Secure Parallel Processing of Big Data Using Order-Preserving Encryption on Google BigQuery}, series = {INFORMATIK 2016, Jahrestagung der Gesellschaft f{\"u}r Informatik e.V., 2016 Proceedings}, volume = {259}, booktitle = {INFORMATIK 2016, Jahrestagung der Gesellschaft f{\"u}r Informatik e.V., 2016 Proceedings}, publisher = {Gesellschaft f{\"u}r Informatik}, address = {Bonn}, isbn = {978-3-88579-653-4}, doi = {10.48550/arXiv.1608.07981}, pages = {343 -- 352}, abstract = {With the increase of centralization of resources in IT-infrastructure and the growing amount of cloud services, database management systems (DBMS) will be more and more outsourced to Infrastructure-as-a-Service (IaaS) providers. The outsourcing of entire databases, or the computation power for processing Big Data to an external provider also means that the provider has full access to the information contained in the database. In this article we propose a feasible solution with Order-Preserving Encryption (OPE) and further, state of the art, encryption methods to sort and process Big Data on external resources without exposing the unencrypted data to the IaaS provider. We also introduce a proof-of-concept client for Google BigQuery as example IaaS Provider.}, language = {en} } @inproceedings{JohannssenBiemannRemusetal., author = {Johannßen, Dirk and Biemann, Chris and Remus, Steffen and Baumann, Timo and Scheffer, David}, title = {GermEval 2020 Task 1 on the Classification and Regression of Cognitive and Motivational style from Text}, series = {Proceedings of the 5th SwissText \& 16th KONVENS Joint Conference 2020}, booktitle = {Proceedings of the 5th SwissText \& 16th KONVENS Joint Conference 2020}, address = {Zurich, Switzerland}, pages = {1 -- 10}, abstract = {This paper describes the tasks, databases, baseline systems, and summarizes submissions and results for the GermEval 2020 Shared Task 1 on the Classification and Regression of Cognitive and Motivational Style from Text. This shared task is divided into two subtasks, a regression task, and a classification task. Subtask 1 asks participants to reproduce a ranking of students based on average aptitude indicators such as different high school grades and different IQ scores. The second subtask aims to classify so-called implicit motives, which are projective testing procedures that can reveal unconscious desires. Besides five implicit motives, the target labels of Subtask 2 also contain one of six levels that describe the type of self-regulation when acting out a motive, which makes this task a multiclass-classification with 30 target labels. 3 participants submitted multiple systems. Subtask 1 was solved (best r = .3701) mainly with non-neural systems and statistical language representations, submissions for Subtask 2 utilized neural approaches and word embeddings (best macro F1 = 70.40). Not only were the tasks solvable, analyses by the participants even showed connections to the implicit psychometrics theory and behavioral observations made by psychologists. This paper describes the tasks, databases, baseline systems, and summarizes submissions and results for the GermEval 2020 Shared Task 1 on the Classification and Regression of Cognitive and Motivational Style from Text. This shared task is divided into two subtasks, a regression task, and a classification task. Subtask 1 asks participants to reproduce a ranking of students based on average aptitude indicators such as different high school grades and different IQ scores. The second subtask aims to classify so-called implicit motives, which are projective testing procedures that can reveal unconscious desires. Besides five implicit motives, the target labels of Subtask 2 also contain one of six levels that describe the type of self-regulation when acting out a motive, which makes this task a multiclass-classification with 30 target labels. 3 participants submitted multiple systems. Subtask 1 was solved (best r =.3701) mainly with non-neural systems and statistical language representations, submissions for Subtask 2 utilized neural approaches and word embeddings (best macro F1 = 70.40). Not only were the tasks solvable, analyses by the participants even showed connections to the implicit psychometrics theory and behavioral observations made by psychologists.}, language = {en} } @article{GegenfurtnerBoucheixGruberetal., author = {Gegenfurtner, Andreas and Boucheix, Jean-Michel and Gruber, Hans and Hauser, Florian and Lehtinen, Erno and Lowe, Richard K.}, title = {The gaze relational index as a measure of visual expertise}, series = {Journal of Expertise}, volume = {3}, journal = {Journal of Expertise}, number = {March}, publisher = {Michigan State University}, issn = {2573-2773}, pages = {32 -- 40}, abstract = {Eye tracking is a powerful technique that helps reveal how people process visual information. This paper discusses a novel metric for indicating expertise in visual information processing. Named the Gaze Relational Index (GRI), this metric is defined as the ratio of mean fixation duration to fixation count. Data from two eye-tracking studies of professional vision and visual expertise in using 3D dynamic medical visualizations are presented as cases to illustrate the suitability and additional benefits of the GRI. Calculated values of the GRI were higher for novices than for experts, and higher in non-representative, semi-familiar / unfamiliar task conditions than in domain-representative familiar tasks. These differences in GRI suggest that, compared to novices, experts engaged in more knowledge-driven, top-down processing that was characterized by quick, exploratory visual search. We discuss future research aiming to replicate the GRI in professional domains with complex visual stimuli and to identify the moderating role of cognitive ability on GRI estimates.}, language = {en} } @inproceedings{HusseinMeyerSickendiekBaumann, author = {Hussein, Hussein and Meyer-Sickendiek, Burkhard and Baumann, Timo}, title = {Free Verse and Beyond: How to Classify Post-modern Spoken Poetry}, series = {Proceedings of Speech Prosody: Tokyo, Japan, 25-28 May 2020}, booktitle = {Proceedings of Speech Prosody: Tokyo, Japan, 25-28 May 2020}, publisher = {ISCA}, doi = {10.21437/SpeechProsody.2020-141}, pages = {690 -- 694}, abstract = {This paper presents the classification of rhythmical patterns detected in post-modern spoken poetry by means of machine learning algorithms that use manually engineered features or automatically learnt representations. We used the world's largest corpus of spoken poetry from our partner lyrikline. We identified nine rhythmical patterns within a spectrum raging from a more fluent to a more disfluent poetic style. The text data analyzed by a statistical parser. Prosodic features of rhythmical patterns are identified by using the parser information. For the classification of rhythmical patterns, we used a neural networks-based approach which use text, audio, and pause information between poetic lines as features. Different combinations of features as well as the integration of feature engineering in the neural networks-based approach are tested. We compared the performance of both approaches (feature-based and neural network-based) using combinations of different features. The results show - by using the weighted average of f-measure for the evaluation - that the neural networks-based approach performed much better in classification of rhythmical patterns. The important improvement of the classification results lies in the use of the audio information. The integration of feature engineering in the neural networks-based approach yielded a very small result improvement.}, language = {en} } @inproceedings{BaumannMeyerSickendiek, author = {Baumann, Timo and Meyer-Sickendiek, Burkhard}, title = {Deep Learning meets Post-modern Poetry}, series = {TwinTalks 2020: Understanding and Facilitating Collaboration in Digital Humanities 2020, proceedings of the Twin Talks 2 and 3 workshops at DHN 2020 and DH 2020, Ottawa Canada and Riga Latvia, July 23 and October 20, 2020}, booktitle = {TwinTalks 2020: Understanding and Facilitating Collaboration in Digital Humanities 2020, proceedings of the Twin Talks 2 and 3 workshops at DHN 2020 and DH 2020, Ottawa Canada and Riga Latvia, July 23 and October 20, 2020}, editor = {Krauwer, Steven and Fišer, Darja}, publisher = {RWTH Aachen}, issn = {1613-0073}, pages = {30 -- 36}, abstract = {We summarize our project Rhythmicalizer in which we analyze a corpus of post-modern poetry in a combination of qualitative hermeneutical and computational methods, as we have run the project over the course of the past three years (and preparing it for some time before that). Interdisciplinary work is always challenging and we here focus on some of the highlights of our collaboration.}, language = {en} } @inproceedings{Baumann, author = {Baumann, Timo}, title = {How a Listener Influences the Speaker}, series = {Proceedings of Speech Prosody: Tokyo, Japan, 25-28 May 2020}, booktitle = {Proceedings of Speech Prosody: Tokyo, Japan, 25-28 May 2020}, publisher = {ISCA}, doi = {10.21437/SpeechProsody.2020-198}, pages = {970 -- 974}, abstract = {Listeners typically provide feedback while listening to a speaker in conversation and thereby engage in the co-construction of the interaction. We analyze the influence of the listener on the speaker by investigating how her verbal feedback signals help in modeling the speaker's language. We find that feedback from the listener may help in modeling the speaker's language, whether through the listener's feedback as transcribed, or the acoustic signal directly. We find the largest positive effects for end of sentence as well as for pauses mid-utterance, but also effects that indicate we successfully model elaborations of ongoing utterances that may result from the presence or absence of listener feedback.}, language = {en} } @article{BaumannKoehnHennig, author = {Baumann, Timo and K{\"o}hn, Arne and Hennig, Felix}, title = {The Spoken Wikipedia Corpus collection: Harvesting, alignment and an application to hyperlistening}, series = {Language Resources and Evaluation}, volume = {53}, journal = {Language Resources and Evaluation}, number = {2}, publisher = {Springer Nature}, doi = {10.1007/s10579-017-9410-y}, pages = {303 -- 329}, abstract = {Spoken corpora are important for speech research, but are expensive to create and do not necessarily reflect (read or spontaneous) speech 'in the wild'. We report on our conversion of the preexisting and freely available Spoken Wikipedia into a speech resource. The Spoken Wikipedia project unites volunteer readers of Wikipedia articles. There are initiatives to create and sustain Spoken Wikipedia versions in many languages and hence the available data grows over time. Thousands of spoken articles are available to users who prefer a spoken over the written version. We turn these semi-structured collections into structured and time-aligned corpora, keeping the exact correspondence with the original hypertext as well as all available metadata. Thus, we make the Spoken Wikipedia accessible for sustainable research. We present our open-source software pipeline that downloads, extracts, normalizes and text-speech aligns the Spoken Wikipedia. Additional language versions can be exploited by adapting configuration files or extending the software if necessary for language peculiarities. We also present and analyze the resulting corpora for German, English, and Dutch, which presently total 1005 h and grow at an estimated 87 h per year. The corpora, together with our software, are available via http://islrn.org/resources/684-927-624-257-3/. As a prototype usage of the time-aligned corpus, we describe an experiment about the preferred modalities for interacting with information-rich read-out hypertext. We find alignments to help improve user experience and factual information access by enabling targeted interaction.}, language = {en} } @inproceedings{SabooBaumann, author = {Saboo, Ashutosh and Baumann, Timo}, title = {Integration of Dubbing Constraints into Machine Translation}, series = {Proceedings of the Fourth Conference on Machine Translation, Volume 1: Research Papers}, booktitle = {Proceedings of the Fourth Conference on Machine Translation, Volume 1: Research Papers}, editor = {Bojar, Ondřej and Chatterjee, Rajen and Federmann, Christian and Fishel, Mark and Graham, Yvette and Haddow, Barry and Huck, Matthias and Yepes, Antonio Jimeno and Koehn, Philipp and Martins, Andr{\´e} and Monz, Christof and Negri, Matteo and N{\´e}v{\´e}ol, Aur{\´e}lie and Neves, Mariana and Post, Matt and Turchi, Marco and Verspoor, Karin}, publisher = {Association for Computational Linguistics}, address = {Stroudsburg, PA, USA}, doi = {10.18653/v1/W19-5210}, pages = {94 -- 101}, abstract = {Translation systems aim to perform a meaning-preserving conversion of linguistic material (typically text but also speech) from a source to a target language (and, to a lesser degree, the corresponding socio-cultural contexts). Dubbing, i.e., the lip-synchronous translation and revoicing of speech adds to this constraints about the close matching of phonetic and resulting visemic synchrony characteristics of source and target material. There is an inherent conflict between a translation's meaning preservation and 'dubbability' and the resulting trade-off can be controlled by weighing the synchrony constraints. We introduce our work, which to the best of our knowledge is the first of its kind, on integrating synchrony constraints into the machine translation paradigm. We present first results for the integration of synchrony constraints into encoder decoder-based neural machine translation and show that considerably more 'dubbable' translations can be achieved with only a small impact on BLEU score, and dubbability improves more steeply than BLEU degrades.}, language = {en} }