Accession Number:

ADA160008

Title:

Speech Recognition: Acoustic, Phonetic and Lexical

Descriptive Note:

End of fiscal year rept. 1 Oct 1984-30 Sep 1985

Corporate Author:

MASSACHUSETTS INST OF TECH CAMBRIDGE RESEARCH LAB OF ELECTRONICS

Personal Author(s):

Report Date:

1985-10-01

Pagination or Media Count:

6.0

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.

Subject Categories:

  • Linguistics
  • Psychology
  • Voice Communications

Distribution Statement:

APPROVED FOR PUBLIC RELEASE