Speech Recognition: Acoustic, Phonetic and Lexical

Abstract

Our long-term research goal is the development and implementation of speaker-independent continuous speech recognition systems. It is our conviction that proper utilization of speech-specific knowledge is essential for advanced speech recognition systems. With this in mind, we have continued to make progress on the acquisition of acoustic-phonetic and lexical knowledge. We have completed the development of a continuous digit recognition system. The system was constructed to investigate the utilization of acoustic phonetic knowledge in a speech recognition system. Some of the significant development of this study includes a soft-failure procedure for lexical access, and the discovery of a set of acoustic-phonetic features for verification. We have completed a study of the constraints provided by lexical stress on word recognition. We found that lexical stress information alone can, on the average, reduce the number of word candidates from a large dictionary by more than 80%. In conjunction with this study, we successfully developed a system that automatically determines the stress pattern of a word from the acoustic signal.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 01, 1985
Accession Number
ADA160008

Entities

People

  • V. W. Zue

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Abstracts
  • Acoustic Signals
  • Acquisition
  • Automated Speech Recognition
  • Case Studies
  • Consonants
  • Dictionaries
  • Information Science
  • Language
  • Massachusetts
  • Military Research
  • Recognition
  • Speech
  • Speech Analysis
  • Technical Information Centers
  • Vocabulary
  • Word Recognition

Readers

  • Speech Processing/Speech Recognition.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation