| Presentation | 2000/6/15 SP2000-11 Selective training of speaker-clustered HMMs Shoei SATO, Hiroyuki SEGI, Kazuo ONOE, Toru IMAI, Hideki TANAKA, Akio ANDO, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper proposes a method of constructing acoustic models for automatic news subtitling. In this method, two-stage clustering is used for an adaptation-data selection from a large-scale database. The first stage generates GMMs from a small amount of data and second atage clusters a large-scale database by the GMMs. A broadcast news transcription experiment showed that the proposed method reduced in toth a word error rate and processing time. The best result in the experiment showed 33% WER reduction and 25% decoding time reduction compared with the baseline method, which had no clustering. Furthermore, we found that it takes just 0.4 seconds from the beginning of an input utterance to select an HMM correctly. The result showed 18% processing time reduction in total compared with the baseline method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Broadcast news / subtitling / speech recognition / acoustic model / HMM / clustering / GMM |
| Paper # | SP2000-11 |
| 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) | SP2000-11 Selective training of speaker-clustered HMMs |
| Sub Title (in English) | |
| Keyword(1) | Broadcast news |
| Keyword(2) | subtitling |
| Keyword(3) | speech recognition |
| Keyword(4) | acoustic model |
| Keyword(5) | HMM |
| Keyword(6) | clustering |
| Keyword(7) | GMM |
| 1st Author's Name | Shoei SATO |
| 1st Author's Affiliation | NHK Science & Technical Research Laboratories() |
| 2nd Author's Name | Hiroyuki SEGI |
| 2nd Author's Affiliation | NHK Science & Technical Research Laboratories |
| 3rd Author's Name | Kazuo ONOE |
| 3rd Author's Affiliation | NHK Science & Technical Research Laboratories |
| 4th Author's Name | Toru IMAI |
| 4th Author's Affiliation | NHK Science & Technical Research Laboratories |
| 5th Author's Name | Hideki TANAKA |
| 5th Author's Affiliation | NHK Science & Technical Research Laboratories |
| 6th Author's Name | Akio ANDO |
| 6th Author's Affiliation | NHK Science & Technical Research Laboratories |
| Date | 2000/6/15 |
| Paper # | SP2000-11 |
| Volume (vol) | vol.100 |
| Number (no) | 136 |
| Page | pp.pp.- |
| #Pages | 7 |
| Date of Issue | |