On speaker-specific prosodic models for automatic dialog act segmentation of multi-party meetings

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F06%3A00500994" target="_blank" >RIV/49777513:23520/06:00500994 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
On speaker-specific prosodic models for automatic dialog act segmentation of multi-party meetings
Original language description
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 theirspeech. 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.
Czech name
—
Czech description
—

Project
<a href="/en/project/1M0567" target="_blank" >1M0567: Centre for Applied Cybernetics</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2006
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Interspeech 2006 and 9th International Conference on Spoken Language Processing
ISBN
978-1-60423-449-7
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
—
Publisher name
Curran Associates, Inc.
Place of publication
Red Hook, NY
Event location
Pittsburgh
Event date
Sep 21, 2006
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000269965901241

Similar results(10)