Method for recognizing speech using linguistically-motivated hidden Markov models
US5268990A · kind A · utility
Assignee
Inventors
Key dates
| Filing date | Jan 31, 1991 |
| Grant date | Dec 7, 1993 |
| Priority date | — |
| Expiry date | Jan 31, 2011 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/142
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
An automatic speech recognition methodology takes advantage of linguistic constraints wherein words are modeled as probabilistic networks of phonetic segments (herein phones), and each phone is represented as a context-independent hidden Markov phone model mixed with a number of context-dependent phone models. Recognition is based on use of methods to design phonological rule sets based on measures of coverage and overgeneration of pronunciations which achieves high coverage of pronunciations with compact representations. Further, a method estimates probabilities of the different possible pronunciations of words. A further method models cross-word coarticulatory effects. In a specific embodiment of the system, a specific method determines the single most-likely pronunciation of words. In further specific embodiments of the system, methods generate speaker-dependent pronunciation networks.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.