| Presentation | 2000/6/15 SP2000-10 Speaker Clustering using Telephone Speech Database of a Large Number of Speakers Tsuneo Kato, Shingo Kuroiwa, Tohru Shimizu, Norio Higuchi, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Speaker clustering is a method that creates groups of speakers with similar acoustic characteristics, and acoustic models tuned to specific groups of speakers are available. Previous researches made on small numbers of training speakers have shown that the recognition accuracy of the speaker-cluster models is not enough. In this paper, a telephone speech database of over a thousand speakers is used for speaker clustering. As a larger number of speakers'data are available, the sparse data problems of both the speakers and the amount of data for each speaker-cluster model are expected to diminish. Experimental results showed the increase of training speakers is very effective for improving phoneme accuracy. Furthermore we estimated the maximal phoneme accuracy possibly obtained with given data. Results showed sixty percent of the difference between phoneme accuracy of speaker-independent and speaker-dependent models may by improved. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | speech recognition / telephone speech / acoustic modeling / speaker adaptation / clustering |
| Paper # | SP2000-10 |
| Date of Issue |
| Conference Information | |
| Committee | SP |
|---|---|
| Conference Date | 2000/6/15(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) | SP2000-10 Speaker Clustering using Telephone Speech Database of a Large Number of Speakers |
| Sub Title (in English) | |
| Keyword(1) | speech recognition |
| Keyword(2) | telephone speech |
| Keyword(3) | acoustic modeling |
| Keyword(4) | speaker adaptation |
| Keyword(5) | clustering |
| 1st Author's Name | Tsuneo Kato |
| 1st Author's Affiliation | KDD R&D Laboratories Inc.() |
| 2nd Author's Name | Shingo Kuroiwa |
| 2nd Author's Affiliation | KDD R&D Laboratories Inc. |
| 3rd Author's Name | Tohru Shimizu |
| 3rd Author's Affiliation | KDD R&D Laboratories Inc. |
| 4th Author's Name | Norio Higuchi |
| 4th Author's Affiliation | KDD R&D Laboratories Inc. |
| Date | 2000/6/15 |
| Paper # | SP2000-10 |
| Volume (vol) | vol.100 |
| Number (no) | 136 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |