@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} }