Speech Recognition: Acoustic Phonetic and Lexical Knowledge Representation.
Status rept. 1 Jul-31 Dec 83,
MASSACHUSETTS INST OF TECH CAMBRIDGE RESEARCH LAB OF ELECTRONICS
Pagination or Media Count:
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.