@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} } @incollection{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 = {Dialogues with social robots: Enablements analyses and evaluation}, booktitle = {Dialogues with social robots: Enablements analyses and evaluation}, editor = {Jokinen, Kristiina and Wilcock, Graham}, publisher = {Springer}, address = {Singapore}, isbn = {978-981-10-2584-6}, doi = {10.1007/978-981-10-2585-3_35}, pages = {421 -- 432}, 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{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{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{BaumannSchlangen, author = {Baumann, Timo and Schlangen, David}, title = {The INPROTK 2012 release}, series = {Sprachkommunikation 2012 : Beitr{\"a}ge zur 10. ITG-Fachtagung vom 26. bis 28. September 2012 in Braunschweig}, booktitle = {Sprachkommunikation 2012 : Beitr{\"a}ge zur 10. ITG-Fachtagung vom 26. bis 28. September 2012 in Braunschweig}, editor = {Fingscheidt, T.}, publisher = {VDE-Verl}, address = {Berlin ; Offenbach}, isbn = {978-3-8007-3455-9}, pages = {147 -- 150}, abstract = {We describe the 2012 release of INPROTK1, our "Incremental Processing Toolkit" which combines a powerful and extensible architecture for incremental processing with components for incremental speech recognition and, new to this release, incremental speech synthesis. These components work domainindependently; we also provide example implementations of higher-level components such as natural language understanding and dialogue management that are somewhat more tied to a particular domain. The toolkit is accompanied by evaluation tools for analysing timing behaviour, and we highlight some timing results on conversational speech input in this paper. We offer our toolkit to foster research in this new and exciting area, which promises to help increase the naturalness of behaviours that can be modelled in such systems.}, language = {en} } @inproceedings{BuschmeierBaumannDorschetal., author = {Buschmeier, Hendrik and Baumann, Timo and Dorsch, Benjamin and Kopp, Stefan and Schlangen, David}, title = {Combining Incremental Language Generation and Incremental Speech Synthesis for Adaptive Information Presentation}, series = {SIGDIAL '12: Proceedings of the 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Seoul, South Korea, July 5 - 6, 2012}, booktitle = {SIGDIAL '12: Proceedings of the 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Seoul, South Korea, July 5 - 6, 2012}, publisher = {Association for Computational Linguistics}, doi = {10.5555/2392800.2392852}, pages = {295 -- 303}, abstract = {Participants in a conversation are normally receptive to their surroundings and their interlocutors, even while they are speaking and can, if necessary, adapt their ongoing utterance. Typical dialogue systems are not receptive and cannot adapt while uttering. We present combin-able components for incremental natural lan-guage generation and incremental speech syn-thesis and demonstrate the flexibility they can achieve with an example system that adapts to a listener's acoustic understanding problems by pausing, repeating and possibly rephrasing problematic parts of an utterance. In an evaluation, this system was rated as significantly more natural than two systems representing the current state of the art that either ignore the interrupting event or just pause; it also has a lower response time.}, language = {en} } @inproceedings{HeintzeBaumannSchlangen, author = {Heintze, Silvan and Baumann, Timo and Schlangen, David}, title = {Comparing Local and Sequential Models for Statistical Incremental Natural Language Understanding}, series = {SIGDIAL '10: Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Tokyo, Japan,September 24 - 25, 2010}, booktitle = {SIGDIAL '10: Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Tokyo, Japan,September 24 - 25, 2010}, publisher = {Association for Computational Linguistics}, address = {Tokyo, Japan}, isbn = {978-1-932432-85-5}, doi = {10.5555/1944506.1944508}, abstract = {Incremental natural language understanding is the task of assigning semantic representations to successively larger prefixes of utterances. We compare two types of statistical models for this task: a) local models, which predict a single class for an input; and b), sequential models, which align a sequence of classes to a sequence of input tokens. We show that, with some modifications, the first type of model can be improved and made to approximate the output of the second, even though the latter is more informative. We show on two different data sets that both types of model achieve comparable performance (significantly better than a baseline), with the first type requiring simpler training data. Results for the first type of model have been reported in the literature; we show that for our kind of data our more sophisticated variant of the model performs better.}, language = {en} } @article{BaumannBussSchlangen, author = {Baumann, Timo and Buß, Okko and Schlangen, David}, title = {Evaluation and Optimisation of Incremental Processors}, series = {Dialogue \& Discourse}, volume = {2}, journal = {Dialogue \& Discourse}, number = {1}, publisher = {OJS}, doi = {10.5087/dad.2011.106}, pages = {113 -- 141}, abstract = {Incremental spoken dialogue systems, which process user input as it unfolds, pose additionalengineering challenges compared to more standard non-incremental systems: Their processingcomponents must be able to accept partial, and possibly subsequently revised input, and mustproduce output that is at the same time as accurate as possible and delivered with as little delay aspossible. In this article, we define metrics that measure how well a given processor meets thesechallenges, and we identify types of gold standards for evaluation. We exemplify these metrics inthe evaluation of several incremental processors that we have developed. We also present genericmeans to optimise some of the measures, if certain trade-offs are accepted. We believe that thiswork will help enable principled comparison of components for incremental dialogue systems andportability of results.}, language = {en} } @inproceedings{BussBaumannSchlangen, author = {Buß, Okko and Baumann, Timo and Schlangen, David}, title = {Collaborating on Utterances with a Spoken Dialogue System Using an ISU-based Approach to Incremental Dialogue Management}, series = {SIGDIAL 10, Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Tokyo Japan September 24 - 25, 2010}, booktitle = {SIGDIAL 10, Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Tokyo Japan September 24 - 25, 2010}, publisher = {Association for Computational Linguistics}, address = {Tokyo, Japan}, isbn = {978-1-932432-85-5}, abstract = {When dialogue systems, through theuse of incremental processing, arenot bounded anymore by strict, non-overlapping turn-taking, a whole range ofadditional interactional devices becomesavailable. We explore the use of one suchdevice, trial intonation. We elaborateour approach to dialogue managementin incremental systems, based on theInformation-State-Update approach, anddiscuss an implementation in a micro-domain that lends itself to the use ofimmediate feedback, trial intonations andexpansions. In an overhearer evaluation,the incremental system was judged as sig-nificantly more human-like and reactivethan a non-incremental version.}, language = {en} } @inproceedings{vonderMalsburgBaumannSchlangen, author = {von der Malsburg, Titus and Baumann, Timo and Schlangen, David}, title = {TELIDA: A Package for Manipulation and Visualisation of Timed Linguistic Data}, series = {Proceedings of the SIGDIAL 2009 Conference: The 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue, September 11 - 12, 2009, London United Kingdom}, booktitle = {Proceedings of the SIGDIAL 2009 Conference: The 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue, September 11 - 12, 2009, London United Kingdom}, publisher = {Association for Computational Linguistics}, address = {London, UK}, doi = {10.5555/1708376.1708419}, pages = {302 -- 305}, abstract = {We present a toolkit for manipulating andvisualising time-aligned linguistic datasuch as dialogue transcripts or languageprocessing data. The package comple-ments existing editing tools by allowingfor conversion between their formats, in-formation extraction from the raw files,and by adding sophisticated, and easily ex-tended methods for visualising the dynam-ics of dialogue processing. To illustratethe versatility of the package, we describeits use in three different projects at our site.}, language = {en} }