Skip to content

Publications

Detail of publication

Citation

Kolář, J. and Shriberg, E. and Liu, Y. : On speaker-specific prosodic models for automatic dialog act segmentation of multi-party meetings . Interspeech, vol. 1, p. 2014-2017, ISCA, Bonn, 2006.

Download PDF

PDF

Abstract

We explore speaker-specific prosodic modeling for dialog act segmentation of speech from the ICSI Meeting Corpus. We ask whether features beyond pauses help individual speakers, and whether some speakers benefit from prosody models trained on only their speech. We find positive results for both questions, although the second is more complex. Feature analysis reveals that duration is the most used feature type, followed by pause and pitch features. Results also suggest a difference between native and nonnative speakers in feature usage patterns. We conclude that features beyond pauses are useful for dialog act segmentation in natural conversation, and that for some speakers, speaker-specific training yields further gains.

Detail of publication

Title: On speaker-specific prosodic models for automatic dialog act segmentation of multi-party meetings
Author: Kolář, J. ; Shriberg, E. ; Liu, Y.
Language: English
Date of publication: 17 Sep 2006
Year: 2006
Type of publication: Papers in journals
Title of journal or book: Interspeech
Číslo vydání: 1
Page: 2014 - 2017
ISBN: 1990-9772
ISSN: 1990-9772
Publisher: ISCA
Address: Bonn
Date: 17 Sep 2006 - 21 Sep 2006
/ 2008-04-18 14:26:52 /

Keywords

automatic speech understanding, prosody, multiparty meetings, dialog acts

BibTeX

@ARTICLE{KolarJ_2006_Onspeaker-specific,
 author = {Kol\'{a}\v{r}, J. and Shriberg, E. and Liu, Y.},
 title = {On speaker-specific prosodic models for automatic dialog act segmentation of multi-party meetings},
 year = {2006},
 publisher = {ISCA},
 journal = {Interspeech},
 address = {Bonn},
 volume = {1},
 pages = {2014-2017},
 ISBN = {1990-9772},
 ISSN = {1990-9772},
 url = {http://www.kky.zcu.cz/en/publications/KolarJ_2006_Onspeaker-specific},
}