@inproceedings{BaumannBussAttereretal., author = {Baumann, Timo and Buß, Okko and Atterer, Michaela and Schlangen, David}, title = {Evaluating the Potential Utility of ASR N-Best Lists for Incremental Spoken Dialogue Systems}, series = {Proceedings of Interspeech 2009 : speech and intelligence ; 6 - 10 September, 2009, Brighton, UK}, booktitle = {Proceedings of Interspeech 2009 : speech and intelligence ; 6 - 10 September, 2009, Brighton, UK}, publisher = {ISCA}, address = {Brighton, UK}, doi = {10.21437/Interspeech.2009-318}, pages = {1031 -- 1034}, abstract = {The potential of using ASR n-best lists for dialogue systems has often been recognised (if less often realised): it is often the case that even when the top-ranked hypothesis is erroneous, a bet- ter one can be found at a lower rank. In this paper, we describe metrics for evaluating whether the same potential carries over to incremental dialogue systems, where ASR output is consumed and reacted upon while speech is still ongoing. We show that even small N can provide an advantage for semantic process- ing, at a cost of a computational overhead.}, 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} } @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} }