| Presentation | 2009-12-21 Speaker Adaptation Using Nonlinear Spectral Transformation For Speech Recognition Toyohiro HAYASHI, Yoshihiko NANKAKU, Akinobu LEE, Keiichi TOKUDA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper proposes a speaker adaptation technique using nonlinear spectral transform based on GMMs. One of the most popular forms of speaker adaptation is based on linear transforms, such as maximum likelihood linear regression(MLLR). In MLLR, model parameters of HMMs are linearly transformed based on the maximum likelihood(ML)fashion by using a small amount of adaptation data. Although multiple transform matrices are used according to the regression class information, only a single linear transform is applied to each state within a regression class. In the proposed technique, we define a new likelihood function combining HMMs for recognition with GMMs for spectral transform and speaker adaptation based on nonlinear transform is performed in the ML fashion. In phoneme recognition experiments, the proposed technique shows better performance than the conventional MLLR approaches. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Speech Recognition / Speaker Adaptation / Nonlinear Spectral Transformation |
| Paper # | NLC2009-12,SP2009-76 |
| Date of Issue |
| Conference Information | |
| Committee | NLC |
|---|---|
| Conference Date | 2009/12/14(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) | Speaker Adaptation Using Nonlinear Spectral Transformation For Speech Recognition |
| Sub Title (in English) | |
| Keyword(1) | Speech Recognition |
| Keyword(2) | Speaker Adaptation |
| Keyword(3) | Nonlinear Spectral Transformation |
| 1st Author's Name | Toyohiro HAYASHI |
| 1st Author's Affiliation | Department of Computer Science and Engineering, Nagoya Institute of Technology() |
| 2nd Author's Name | Yoshihiko NANKAKU |
| 2nd Author's Affiliation | Department of Computer Science and Engineering, Nagoya Institute of Technology |
| 3rd Author's Name | Akinobu LEE |
| 3rd Author's Affiliation | Department of Computer Science and Engineering, Nagoya Institute of Technology |
| 4th Author's Name | Keiichi TOKUDA |
| 4th Author's Affiliation | Department of Computer Science and Engineering, Nagoya Institute of Technology |
| Date | 2009-12-21 |
| Paper # | NLC2009-12,SP2009-76 |
| Volume (vol) | vol.109 |
| Number (no) | 355 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |