| Presentation | 2000/12/14 Multiple-Regression HMM for Speech Variability Katsuhisa Fujinaga, Mitsuru Nakai, Hiroshi Shimodaira, Shigeki Sagayama, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper proposes a new class of hidden Markov model (HMM) called multiple-regression HMM that utilizes auxiliary features such as fundamental frequency (F_0) and speaking styles that affect spectral parameters to better model the acoustic features of phonemes. Though such auxiliary features are considered to be the factors that degrade the performance of speech recognizers, the proposed MR-HMM adapts its model parameters, i. e. mean vectors of output probability distributions, depending on these auxiliary information to improve the recognition accuracy. Formulation for parameter reestimation of MR-HMM based on the EM algorithm is given in the paper. Speaker-dependent speech recognition expriments demonstrated that error rates reduced by more than 15.3% and 22.0% in phoneme and isolated word recognition, respectively, compared with the conventional HMMs. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | speech recognition / hidden Markov model / multiple-regression model / F_0 / adaptation |
| Paper # | NLC2000-35,SP2000-83 |
| Date of Issue |
| Conference Information | |
| Committee | NLC |
|---|---|
| Conference Date | 2000/12/14(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) | Multiple-Regression HMM for Speech Variability |
| Sub Title (in English) | |
| Keyword(1) | speech recognition |
| Keyword(2) | hidden Markov model |
| Keyword(3) | multiple-regression model |
| Keyword(4) | F_0 |
| Keyword(5) | adaptation |
| 1st Author's Name | Katsuhisa Fujinaga |
| 1st Author's Affiliation | School of Information Science, Japan Advanced Institute of Science and Technology() |
| 2nd Author's Name | Mitsuru Nakai |
| 2nd Author's Affiliation | School of Information Science, Japan Advanced Institute of Science and Technology |
| 3rd Author's Name | Hiroshi Shimodaira |
| 3rd Author's Affiliation | School of Information Science, Japan Advanced Institute of Science and Technology |
| 4th Author's Name | Shigeki Sagayama |
| 4th Author's Affiliation | School of Information Science, Japan Advanced Institute of Science and Technology : Graduate School of Engineering, University of Tokyo |
| Date | 2000/12/14 |
| Paper # | NLC2000-35,SP2000-83 |
| Volume (vol) | vol.100 |
| Number (no) | 520 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |