@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} }