Speech Recognition: Acoustic Phonetic and Lexical Knowledge Representation.

Abstract

The purpose of this program is to develop a speech data base facility under which the acoustic characteristics of speech sounds in various contexts can be studied conveniently; investigate the phonological properties of a large lexicon of, say 10,000 words and determine to what extent the phonotactic constraints can be utilized in speech recognition; study the acoustic cues that are used to mark work boundaries; develop a test bed in the form of a large-vocabulary, IWR system to study the interactions of acoustic, phonetic and lexical knowledge; and develop a limited continuous speech recognition system with the goal of recognizing any English word from its spelling in order to assess the interactions of higher-level knowledge sources.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 01, 1984
Accession Number
ADA137697

Entities

People

  • V. W. Zue

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Advanced Electronics
  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Accuracy
  • Acoustic Signals
  • Artificial Intelligence
  • Automated Speech Recognition
  • Computer Science
  • Computers
  • Databases
  • Electrical Engineering
  • Engineering
  • Information Science
  • Language
  • Military Research
  • Pattern Recognition
  • Recognition
  • Signal Processing
  • Statistical Analysis
  • Word Recognition

Readers

  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation