Speech Recognition: Acoustic, Phonetic and Lexical Knowledge
Abstract
During this reporting period we continued to make progress on the acquisition of acoustic-phonetic and lexical knowledge. (1)We completed development of a continuous digit recognition system. The system was constructed to investigate the use of acoustic-phonetic knowledge in a speech recognition system. The significant achievements of this study include the development of a 'soft-failure' procedure for lexical access and the discovery of a set of acoustic-phonetic features for verification. (2) We completed a study of the constraints that lexical stress imposes 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 percent. In conjunction with this study, we successfully developed a system that automatically determines the stress pattern of a word from the acoustic signal. (3) We performed an acoustic study on the characteristics of nasal consonants and nasalized vowels. We have also developed recognition algorithms for nasal murmurs and nasalized vowels in continuous speech. (4) We finished the preliminary development of a system that aligns a speech waveform with the corresponding phonetic transcription.
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 05, 1985
- Accession Number
- ADA158264
Entities
People
- V. W. Zue
Organizations
- Massachusetts Institute of Technology