On Speaker-Specific Prosodic Models for Automatic Dialog Act Segmentation of Multi-Party Meetings

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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2006
Accession Number
ADA459018

Entities

People

  • Elizabeth Shriberg
  • Jachym Kolar
  • Yang Liu

Organizations

  • International Computer Science Institute

Tags

Communities of Interest

  • C4I
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Automata Theory
  • Automated Speech Recognition
  • Automatic
  • Boundaries
  • Computational Science
  • Computer Languages
  • Computer Science
  • Computer Vision
  • Czech Republic
  • Data Sets
  • Language
  • Linguistics
  • Machine Learning
  • Natural Language Processing
  • Natural Languages
  • Recognition
  • Test Sets

Fields of Study

  • Linguistics

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Computational Linguistics
  • Military Engineering.