Integrating Prosodic and Lexical Cues for Automatic Topic Segmentation

Abstract

We present a probabilistic model that uses both prosodic and lexical cues for the automatic segmentation of speech into topically coherent units. We propose two methods for combining lexical and prosodic information using hidden Markov models and decision trees. Lexical information is obtained from a speech recognizer, and prosodic features are extracted automatically from speech waveforms. We evaluate our approach on the Broadcast News corpus, using the DARPA-TDT evaluation metrics. Results show that the prosodic model alone is competitive with word-based segmentation methods. Furthermore, we achieve a significant reduction in error by combining the prosodic and word-based knowledge sources.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 2001
Accession Number
ADA580023

Entities

People

  • Andreas Stolcke
  • Dilek Hakkani-tur
  • Elizabeth Shriberg
  • Gokhan Tur

Organizations

  • SRI International

Tags

Communities of Interest

  • Autonomy
  • Human Systems

DTIC Thesaurus Topics

  • Automatic
  • Computational Linguistics
  • Computational Science
  • Computer Vision
  • False Alarms
  • Frequency
  • Hidden Markov Models
  • Information Retrieval
  • Language
  • Linguistics
  • Machine Learning
  • Markov Models
  • Probabilistic Models
  • Probability
  • Signal Processing
  • Statistical Analysis
  • Test Sets

Fields of Study

  • Computer science

Readers

  • Distributed Systems and Data Platform Development
  • Speech Processing/Speech Recognition.