@inproceedings{BaumannBussSchlangen, author = {Baumann, Timo and Buß, Okko and Schlangen, David}, title = {InproTK in Action: Open-Source Software for Building German-Speaking Incremental Spoken Dialogue Systems}, series = {Electronic speech signal processing 2010 : proceedings of the 21st conference, Berlin, 8 - 10 September 2010}, booktitle = {Electronic speech signal processing 2010 : proceedings of the 21st conference, Berlin, 8 - 10 September 2010}, publisher = {TUDpress}, address = {Berlin, Germany}, pages = {204 -- 211}, abstract = {We present INPROTK, a toolkit for building incremental spoken dia-logue systems. Incremental spoken dialogue systems (systems that may react whilethe user's utterance is ongoing) are a fairly recent research topic and allow for ex-citing new features. Even though toolkits exist that help in building conventionaldialogue systems, INPROTK offers both a tested architecture for building incre-mental SDSs as well as many of the building blocks necessary when building suchsystems. With INPROTK a researcher can avoid many of the technical difficulties,which hopefully further fosters research in this area.}, language = {en} } @inproceedings{AttererBaumannSchlangen, author = {Atterer, Michaela and Baumann, Timo and Schlangen, David}, title = {No Sooner Said Than Done: Testing the Incrementality of Semantic Interpretations of Spontaneous Speech}, series = {Proceedings of Interspeech 2009 : 6 - 10 September 2009, Brighton, U.K.}, booktitle = {Proceedings of Interspeech 2009 : 6 - 10 September 2009, Brighton, U.K.}, publisher = {International Speech Communication Association}, address = {Brighton, UK}, doi = {10.21437/Interspeech.2009-539}, pages = {1855 -- 1858}, abstract = {Ideally, a spoken dialogue system should react without much delay to a user's utterance. Such a system would already select an object, for instance, before the user has finished her utterance about moving this particular object to a particular place. A prerequisite for such a prompt reaction is that semantic representations are built up on the fly and passed on to other modules. Few approaches to incremental semantics construction exist, and, to our knowledge, none of those has been systematically tested on a spontaneous speech corpus. In this paper, we develop measures to test empirically on transcribed spontaneous speech to what extent we can create semantic interpretation on the fly with an incremental semantic chunker that builds a frame semantics.}, language = {en} } @inproceedings{BaumannSchlangen, author = {Baumann, Timo and Schlangen, David}, title = {Predicting the Micro-Timing of User Input for an Incremental Spoken Dialogue System that Completes a User's Ongoing Turn}, series = {SIGDIAL 2011 Conference, 12th annual meeting of the Special Interest Group on Discourse and Dialogue, Co-located with ACL HLT 2011, Portland, Oregon, 17 - 18 June 2011}, booktitle = {SIGDIAL 2011 Conference, 12th annual meeting of the Special Interest Group on Discourse and Dialogue, Co-located with ACL HLT 2011, Portland, Oregon, 17 - 18 June 2011}, publisher = {Curran}, address = {Red Hook, NY}, isbn = {978-1-61839-242-8}, pages = {120 -- 129}, abstract = {We present the novel task of predicting tem-poral features of continuations of user input,while that input is still ongoing. We show that the remaining duration of an ongoing word, aswell as the duration of the next can be predicted reasonably well, and we put this information touse in a system that synchronously completesa user's speech. While we focus on collaborative completions, the techniques presented here may also be useful for the alignment of back-channels and immediate turn-taking in anincremental SDS, or to synchronously monitorthe user's speech fluency for other reasons.}, 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} } @incollection{BaumannSchlangen, author = {Baumann, Timo and Schlangen, David}, title = {Interactional Adequacy as a Factor in the Perception of Synthesized Speech}, series = {Proceedings of Speech Synthesis Workshop (SSW8)}, booktitle = {Proceedings of Speech Synthesis Workshop (SSW8)}, address = {Barcelona, Spain}, abstract = {Speaking as part of a conversation is different from reading out aloud. Speech synthesis systems, however, are typically developed using assumptions (at least implicitly) that are more true of the latter than the former situation. We address one particular aspect, which is the assumption that a fully formulated sentence is available for synthesis. We have built a system that does not make this assumption but rather can synthesize speech given incrementally extended input. In an evaluation experiment, we found that in a dynamic domain where what is talked about changes quickly, subjects rated the output of this system as more 'naturally pronounced' than that of a baseline system that employed standard synthesis, despite the synthesis quality objectively being degraded. Our results highlight the importance of considering a synthesizer's ability to support interactive use-cases when determining the adequacy of synthesized speech.}, language = {en} } @inproceedings{BaumannSchlangen, author = {Baumann, Timo and Schlangen, David}, title = {Open-ended, Extensible System Utterances Are Preferred, Even If They Require Filled Pauses}, series = {14th annual meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2013) : Metz, France, 22 - 24 August 2013}, booktitle = {14th annual meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2013) : Metz, France, 22 - 24 August 2013}, publisher = {Curran}, address = {Red Hook, NY}, pages = {280 -- 283}, abstract = {In many environments (e. g. sports commentary), situations incrementally unfold over time and often the future appearance of a relevant event can be predicted, but not in all its details or precise timing. We have built a simulation framework that uses our incremental speech synthesis component to assemble in a timely manner complex commentary utterances. In our evaluation, the resulting output is preferred over that from a baseline system that uses a simpler commenting strategy. Even in cases where the incremental system overcommits temporally and requires a filled pause to wait for the upcoming event, the system is preferred over the baseline.}, language = {en} } @inproceedings{AttererBaumannSchlangen, author = {Atterer, Michaela and Baumann, Timo and Schlangen, David}, title = {Towards Incremental End-of-Utterance Detection in Dialogue Systems}, series = {COLING '08: Proceedings of the 22nd International Conference on Computational Linguistics, Manchester United Kingdom August 18 - 22, 2008}, booktitle = {COLING '08: Proceedings of the 22nd International Conference on Computational Linguistics, Manchester United Kingdom August 18 - 22, 2008}, publisher = {Association for Computational Linguistics}, isbn = {978-1-905593-44-6}, pages = {11 -- 14}, abstract = {We define the task of incremental or 0-lag utterance segmentation, that is, the task of segmenting an ongoing speech recognition stream into utterance units, and present first results. We use a combination of hidden event language model, features from an incremental parser, and acoustic / prosodic features to train classifiers on real-world conversational data (from the Switchboard corpus). The best classifiers reach an F-score of around 56\%, improving over baseline and related work.}, language = {en} } @incollection{BaumannSchlangen, author = {Baumann, Timo and Schlangen, David}, title = {Evaluating Prosodic Processing for Incremental Speech Synthesis}, series = {Proceedings of Interspeech 2012}, booktitle = {Proceedings of Interspeech 2012}, publisher = {International Speech Communication Association}, doi = {10.21437/Interspeech.2012-152}, pages = {438 -- 441}, abstract = {Incremental speech synthesis (iSS) accepts input and produces output in consecutive chunks that only together result in a full utterance. Systems that use iSS thus have the ability to adapt their utterances while they are ongoing. Having available less than the full utterance to plan the acoustic realisation has downsides, however, as global optimisation is not possible anymore. In this paper we present a strategy for incrementalizing the symbolic pre-processing component of speech synthesis and assess the influence of a reduction in "lookahead", i. e. in knowledge about the rest of the utterance, on prosodic quality. We found that high quality incremental output can be achieved even with a lookahead of slightly less than one phrase, allowing for timely system reaction.}, language = {en} } @inproceedings{BaumannSchlangen, author = {Baumann, Timo and Schlangen, David}, title = {Inpro_iSS: A Component for Just-In-Time Incremental Speech Synthesis}, series = {The 13th Conference of the European Chapter of the Association for Computational Linguistics - proceedings of the System Demonstrations, April 23 - 27 2012, Avignon France}, booktitle = {The 13th Conference of the European Chapter of the Association for Computational Linguistics - proceedings of the System Demonstrations, April 23 - 27 2012, Avignon France}, publisher = {Association for Computational Linguistics (ACL)}, abstract = {We present a component for incremental speech synthesis (iSS) and a set of applications that demonstrate its capabilities. This component can be used to increase the responsivity and naturalness of spoken interactive systems. While iSS can show its full strength in systems that generate output incrementally, we also discuss how even otherwise unchanged systems may profit from its capabilities.}, language = {en} } @inproceedings{PeldszusBussBaumannetal., author = {Peldszus, Andreas and Buß, Okko and Baumann, Timo and Schlangen, David}, title = {Joint Satisfaction of Syntactic and Pragmatic Constraints Improves Incremental Spoken Language Understanding}, series = {EACL 2012 Joint Workshop of LINGVIS \& UNCLH, Visualization of Linguistic Patterns and Uncovering Language History from Multilingual Resources, Proceedings of the Workshop, April 23 - 24 2012, Avignon France}, booktitle = {EACL 2012 Joint Workshop of LINGVIS \& UNCLH, Visualization of Linguistic Patterns and Uncovering Language History from Multilingual Resources, Proceedings of the Workshop, April 23 - 24 2012, Avignon France}, publisher = {The Association for Computational Linguistics}, isbn = {978-1-937284-19-0}, pages = {514 -- 523}, abstract = {We present a model of semantic processing of spoken language that (a) is robust against ill-formed input, such as can be expected from automatic speech recognisers, (b) respects both syntactic and pragmatic constraints in the computation of most likely interpretations, (c) uses a principled, expressive semantic representation formalism (RMRS) with a well-defined model theory, and (d) works continuously (producing meaning representations on a word-by-word basis, rather than only for full utterances) and incrementally (computing only the additional contribution by the new word, rather than re-computing for the whole utterance-so-far). We show that the joint satisfaction of syntactic and pragmatic constraints improves the performance of the NLU component (around 10 \% absolute, over a syntax-only baseline).}, 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{SchlangenBaumannAtterer, author = {Schlangen, David and Baumann, Timo and Atterer, Michaela}, title = {Incremental Reference Resolution: The Task, Metrics for Evaluation, and a Bayesian Filtering Model that is Sensitive to Disfluencies}, 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}, pages = {30 -- 37}, abstract = {In this paper we do two things: a) we discuss in general terms the task of incre mental reference resolution (IRR), in particular resolution of exophoric reference, and specify metrics for measuring the performance of dialogue system components tackling this task, and b) we present a simple Bayesian filtering model of IRR that performs reasonably well just using words directly (no structure information and no hand-coded semantics): it picks the right referent out of 12 for around 50 \% of real world dialogue utterances in our test corpus. It is also able to learn to interpret not only words but also hesitations, just as humans have shown to do in similar situations, namely as markers of references tohard-to-describe entities.}, language = {en} } @inproceedings{SchlangenBaumannBuschmeieretal., author = {Schlangen, David and Baumann, Timo and Buschmeier, Hendrik and Buß, Okko and Kopp, Stefan and Skantze, Gabriel and Yaghoubzadeh, Ramin}, title = {Middleware for Incremental Processing in Conversational Agents}, series = {Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SigDial 2010), September 24 - 25, 2010, Tokyo Japan}, booktitle = {Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SigDial 2010), September 24 - 25, 2010, Tokyo Japan}, publisher = {Association for Computational Linguistics}, address = {Tokyo, Japan}, pages = {51 -- 54}, abstract = {We describe work done at three sites on designing conversational agents capable of incremental processing. We focus on the ‘middleware’ layer in these systems, which takes care of passing around and maintaining incremental information between the modules of such agents. All implementations are based on the abstract model of incremental dialogue processing proposed by Schlangen and Skantze (2009), and the paper shows what different instantiations of the model can look like given specific requirements and application areas.}, language = {en} } @incollection{vanWelbergenBaumannSchlangenetal., author = {van Welbergen, Herwin and Baumann, Timo and Schlangen, David and Kopp, Stefan}, title = {Incremental, Adaptive and Interruptive Speech Realization for Fluent Conversation with ECAs}, series = {Intelligent Virtual Agents}, booktitle = {Intelligent Virtual Agents}, publisher = {Springer}, isbn = {978-3-642-40414-6}, pages = {468 -- 469}, abstract = {This project aimed to establish the feasibility of creating a procedural system for generating expressive facial animation based on an affective agent. A procedural system supporting a limited number of emotional expression changes was created alongside keyframed animations of these same emotional expression changes, and audience response to these two approaches was tested empirically. Results seem to partially support the procedural animations generated being comparable with keyframed, in terms of perceptual validity.}, 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} } @inproceedings{BaumannPohlSelgrad, author = {Baumann, Timo and Pohl, Martin and Selgrad, Kai}, title = {Einf{\"u}hrung und erste Evaluation des Selbstlernkonzepts CodeClinic an der OTH Regensburg}, series = {Tagungsband MINT Symposium 2025. Zukunft MINT Lehre: Was bleibt? Was kommt? Was wirkt?}, booktitle = {Tagungsband MINT Symposium 2025. Zukunft MINT Lehre: Was bleibt? Was kommt? Was wirkt?}, editor = {Sch{\"a}fle, Claudia and D{\"o}lling, Hanna}, publisher = {BayZiel - Bayerisches Zentrum f{\"u}r Innovative Lehre}, address = {M{\"u}nchen}, issn = {1612-4537}, doi = {10.35096/othr/pub-8613}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-86138}, pages = {9}, abstract = {Mit der CodeClinic wollen wir das Programmieren-Lernen - eine der großen Einstiegsh{\"u}rden in Informatik- und informatiknahen Studieng{\"a}ngen - in einen Prozess {\"u}berf{\"u}hren, der das gemeinschaftliche Lernen in der Hochschullehre st{\"a}rker als bisher in den Vordergrund r{\"u}ckt. Davon profitieren Studierende in ihrer fachlichen und pers{\"o}nlichen Entwicklung, und das Lernumfeld spiegelt die tats{\"a}chliche Realit{\"a}t der beruflichen Praxis besser wider. Wir unterst{\"u}tzen dieses Konzept durch einen f{\"u}r selbstgesteuertes und gemeinschaftliches Lernen ausgelegten SCALE-UP-Raum, den wir an der OTH Regensburg eingerichtet haben. In unserem Beitrag erl{\"a}utern wir Konzept und Raum und liefern eine erste Evaluation zum Erfolg unserer Maßnahmen.}, subject = {Hochschuldidaktik}, language = {de} }