Method of generating a subword model for speech recognition
US5677988A · kind A · utility
Assignee
Inventors
Key dates
| Filing date | Sep 21, 1995 |
| Grant date | Oct 14, 1997 |
| Priority date | — |
| Expiry date | Sep 21, 2015 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/022
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
An automated method of generating a subword model for speech recognition dependent on phoneme context for processing speech information using a Hidden Markov Model in which static features of speech and dynamic features of speech are modeled as a chain of a plurality of output probability density distributions. The method comprising determining a phoneme context class which is a model unit allocated to each model, the number of states used for representing each model, relationship of sharing of states among a plurality of models, and output probability density distribution of each model, by repeating splitting of a small number of states, provided in an initial Hidden Markov Model, based on a prescribed criterion on a probabilistic model.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.