Summary of the paper
| Title | Construction of Back-Channel Utterance Corpus for Responsive Spoken Dialogue System Development |
|---|---|
| Authors | Yuki Kamiya, Tomohiro Ohno, Shigeki Matsubara and Hideki Kashioka |
| Abstract | In spoken dialogues, if a spoken dialogue system does not respond at all duringuser’s utterances, the user might feel uneasy because the user does not knowwhether or not the system has recognized the utterances. In particular,back-channel utterances, which the system outputs as voices such as “yeah”and “uh huh” in English have important roles for a driver in in-car speechdialogues because the driver does not look owards a listener while driving.This paper describes construction of a back-channel utterance corpus and itsanalysis to develop the system which can output back-channel utterances at theproper timing in the responsive in-car speech dialogue. First, we constructedthe back-channel utterance corpus by integrating the back-channel utterancesthat four subjects provided for the driver’s utterances in 60 dialogues inthe CIAIR in-car speech dialogue corpus. Next, we analyzed the corpus andrevealed the relation between back-channel utterance timings and information on bunsetsu, clause, pause and rate of speech. Based on the analysis, we examinedthe possibility of detecting back-channel utterance timings by machine learningtechnique. As the result of the experiment, we confirmed that our techniqueachieved as same detection capability as a human. |
| Language | Discourse annotation, representation and processing |
| Topics | Dialogue, Speech resource/database, Discourse annotation, representation and processing |
Full paper  |
Construction of Back-Channel Utterance Corpus for Responsive Spoken Dialogue System Development |
| Bibtex | @InProceedings{KAMIYA10.260, author = {Yuki Kamiya, Tomohiro Ohno, Shigeki Matsubara and Hideki Kashioka}, title = {Construction of Back-Channel Utterance Corpus for Responsive Spoken Dialogue System Development}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |