Presentation | 1999/8/5 Speech Recognition and Selection of the Structure of the Hidden Markov Model Using the Genetic Algorithm Tomio Takara, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper describes how to apply the genetic algorithm (GA)to the automatic speech recognition using the hidden Markov model (HMM). First we applied the GA to selection of structure of the discrete HMM for speech recognition. As a result of recognition experiment, the recognition score became higher as the generation proceeded. This was true not only for the training set but also for the test set. The recognition score became higher than that of an HMM with the basic left-to-right structure which is popular and achieves high performance. Next the GA was applied to the continuous HMM, then it was shown that the same effective result is obtained. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Genetic algorithm / Hidden Markov model / Automatic speech recognition / Structure / Optimization |
Paper # | SP99-60 |
Date of Issue |
Conference Information | |
Committee | SP |
---|---|
Conference Date | 1999/8/5(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Speech (SP) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Speech Recognition and Selection of the Structure of the Hidden Markov Model Using the Genetic Algorithm |
Sub Title (in English) | |
Keyword(1) | Genetic algorithm |
Keyword(2) | Hidden Markov model |
Keyword(3) | Automatic speech recognition |
Keyword(4) | Structure |
Keyword(5) | Optimization |
1st Author's Name | Tomio Takara |
1st Author's Affiliation | Department of Information Engineering,University of the Ryukyus() |
Date | 1999/8/5 |
Paper # | SP99-60 |
Volume (vol) | vol.99 |
Number (no) | 255 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |