@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} } @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} }