| Presentation | 1996/12/13 A Study on Improvement of HM-Nets using Decision Tree-based Successive State Splitting Takaaki HORI, Masaharu KATOH, Akinori ITO, Masaki KOHDA, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The important aspects of context-dependent acoustic modeling using a limited training data set for robust speech reognition are how to tie the model parameters and how to handle the unknown contexts. From this point of view, we proposed the Decision Tree-based Successive State Splitting algorithm (DT-SSS), and showed HM-Nets generated with this algorithm had high accuracy and enabled to represent any contexts. But this algorithm was not taken temporal splits into consideration, and therefore did not make the best use of the strong point of SSS. In this paper, we incorporate temporal splits into DT-SSS and generate HM-Nets from various initial models. In continuous phoneme reognition experiments, we show the effects of these improvements. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | speech recognition / hidden Markov model / context-dependent model / hidden Markov network phonetic decision tree |
| Paper # | NLC96-49,SP96-80 |
| Date of Issue |
| Conference Information | |
| Committee | NLC |
|---|---|
| Conference Date | 1996/12/13(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 | Natural Language Understanding and Models of Communication (NLC) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Study on Improvement of HM-Nets using Decision Tree-based Successive State Splitting |
| Sub Title (in English) | |
| Keyword(1) | speech recognition |
| Keyword(2) | hidden Markov model |
| Keyword(3) | context-dependent model |
| Keyword(4) | hidden Markov network phonetic decision tree |
| 1st Author's Name | Takaaki HORI |
| 1st Author's Affiliation | Faculty of Engineering, Yamagata University() |
| 2nd Author's Name | Masaharu KATOH |
| 2nd Author's Affiliation | Faculty of Engineering, Yamagata University |
| 3rd Author's Name | Akinori ITO |
| 3rd Author's Affiliation | Faculty of Engineering, Yamagata University |
| 4th Author's Name | Masaki KOHDA |
| 4th Author's Affiliation | Faculty of Engineering, Yamagata University |
| Date | 1996/12/13 |
| Paper # | NLC96-49,SP96-80 |
| Volume (vol) | vol.96 |
| Number (no) | 420 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |