Presentation | 2000/1/21 Acoustic models for dialogue speech recognition Masato Mimura, Tatsuya Kawahara, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Acoustic models for dialogue speech recognition must be trained using dialogue speech corpus to capture their characteristic features. But there is not so large dialogue speech corpus that contains all acoustic variations of all phone contexts. First, we investigate the effect of using dialogue speech corpus for dialogue speech recognition, and we realize reliable training by adding read speech corpus. Finally, we make use of syllable structures of dialogue speech for more effective training by comining both corpora. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | dialogue speech / context-dependent triphone HMM / decision tree clustering |
Paper # | SP99-140 |
Date of Issue |
Conference Information | |
Committee | SP |
---|---|
Conference Date | 2000/1/21(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) | Acoustic models for dialogue speech recognition |
Sub Title (in English) | |
Keyword(1) | dialogue speech |
Keyword(2) | context-dependent triphone HMM |
Keyword(3) | decision tree clustering |
1st Author's Name | Masato Mimura |
1st Author's Affiliation | Graduate School of Informatics Kyoto University() |
2nd Author's Name | Tatsuya Kawahara |
2nd Author's Affiliation | Graduate School of Informatics Kyoto University |
Date | 2000/1/21 |
Paper # | SP99-140 |
Volume (vol) | vol.99 |
Number (no) | 577 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |