| Presentation | 1999/12/20 Phonetic Tied-Mixture Model for LVCSR Akinobu Lee, Tatsuya Kawahara, Kazuya Takeda, Kiyohiro Shikano, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | A phonetic tied-mixture(PTM)model for efficient large vocabulary continuous speech recognition ispresented. It is synthesized from context-independent phone models with 64mixture components per state by assigning different mixture weights according to the shared states of triphones. Mixtures are then re-estimated for optimization. The model achieves a word error rate of 7.O% at 20k-word dictation of newspaper corpus, which is comparable to the best figure by the triphone of much higher resolutions. Compared with conventional PTMs that share Gaussians by all states, the proposed model is easily trained and reliably estimated. Furthermore, the model enables the decoder to perform efficient Gaussian Pruning. It is found out that computing only two out of 64 components does not cause any loss of accuracy. Several methods for the pruning are proposed and compared, and the best one reduced compared, and the best one reduced the computation to about 20%. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | |
| Paper # | NLC99-100 |
| Date of Issue |
| Conference Information | |
| Committee | NLC |
|---|---|
| Conference Date | 1999/12/20(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) | Phonetic Tied-Mixture Model for LVCSR |
| Sub Title (in English) | |
| Keyword(1) | |
| 1st Author's Name | Akinobu Lee |
| 1st Author's Affiliation | () |
| 2nd Author's Name | Tatsuya Kawahara |
| 2nd Author's Affiliation | |
| 3rd Author's Name | Kazuya Takeda |
| 3rd Author's Affiliation | |
| 4th Author's Name | Kiyohiro Shikano |
| 4th Author's Affiliation | |
| Date | 1999/12/20 |
| Paper # | NLC99-100 |
| Volume (vol) | vol.99 |
| Number (no) | 523 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |