A Robust Loose Coupling for Speech Recognition and Natural Understanding.

Abstract

The focus of this thesis proposal is to improve the ability of a computational system to understand spoken utterances in a dialogue with a human. Available computational methods for word recognition do not perform as well on spontaneous speech as we would hope. Even a state of the art recognizer achieves slightly worse than 70% word accuracy on (nearly) spontaneous speech in a conversation about a specific problem. To address the incrementality of spontaneously spoken utterances, I will develop methods for segmenting a given utterance into 'chunks' representing individual thoughts. Given an utterance of spontaneous speech, a tool for automatic prosodic feature extraction will analyze the output of the error-correcting post-processor and the acoustic waveform to generate prosodic cues. These cues will aid a robust parser using a prosody-wise grammar to identify the incremental phrases in the utterance and to provide a syntactic analysis. These components will augment the TRAINs-95 conversational planning assistant. (AN)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 1995
Accession Number
ADA299910

Entities

People

  • Eric K. Ringger

Organizations

  • University of Rochester

Tags

DTIC Thesaurus Topics

  • Accuracy
  • Automated Speech Recognition
  • Automatic
  • Computational Science
  • Couplings
  • Errors
  • Extraction
  • Feature Extraction
  • Identification
  • Recognition
  • Waveforms
  • Word Recognition

Readers

  • Artificial Intelligence
  • Neural Network Machine Learning.
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation