Automatic Linguistic Segmentation
of Conversational Speech

Andreas Stolcke - Elizabeth Shriberg
Speech Technology and Research Laboratory
SRI International, Menlo Park, CA 94025
stolcke@speech.sri.com
ees@speech.sri.com

Abstract:

As speech recognition moves toward more unconstrained domains such as conversational speech, we encounter a need to be able to segment (or resegment) waveforms and recognizer output into linguistically meaningful units, such a sentences. Toward this end, we present a simple automatic segmenter of transcripts based on N-gram language modeling. We also study the relevance of several word-level features for segmentation performance. Using only word-level information, we achieve 85% recall and 70% precision on linguistic boundary detection.

• node1.html
• Introduction
• The Importance of Linguistic Segmentation
• Method
• The Model
• Results
  • Baseline Segmentation Model
  • Using Turn Information
  • Using Part-of-Speech Information
  • Error Trade-offs
• Discussion
  • Error Analysis
  • Other Segmentation Algorithms
  • Other Features for Segmentation
• Conclusions
• References
• About this document ...