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 phontactic 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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Feb 22, 1983
- Accession Number
- ADA125134
Entities
People
- Victor W. Zue
Organizations
- Massachusetts Institute of Technology