Presentation | 2003/10/24 Evaluation of Speaker Model Selection based on Bayesian Information Criterion in Unsupervised Speaker Indexing Masafumi NISHIDA, Tatsuya KAWAHARA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper addresses unsupervised speaker indexing for discussion audio archives. We have performed the speaker indexing using our proposed framework that selects an optimal speaker model (GMM or VQ) based on the BIC. A threshold of the speaker indexing is needed to be determined in advance because the framework is applied to the speaker indexing in the case where the number of speakers is unknown beforehand. Thus, we evaluate robustness of indexing accuracy when varying the threshold and the indexing accuracy when the number of speakers instead of the threshold is given. As a result of comparison with conventional methods, it is demonstrated that the proposed framework can set up the threshold robustly and archives the higher indexing accuracy in both cases where the number of speakers is unknown or given beforehand. The speaker index is useful for speaker adaptation of the acoustic model, which improves the performance of automatic speech recognition. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Speaker model selection / Bayesian information criterion / Unsupervised speaker indexing / Speaker recognition / Speech recognition / Discussions |
Paper # | SP2003-103,WIT2003-15 |
Date of Issue |
Conference Information | |
Committee | WIT |
---|---|
Conference Date | 2003/10/24(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 | Well-being Information Technology(WIT) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Evaluation of Speaker Model Selection based on Bayesian Information Criterion in Unsupervised Speaker Indexing |
Sub Title (in English) | |
Keyword(1) | Speaker model selection |
Keyword(2) | Bayesian information criterion |
Keyword(3) | Unsupervised speaker indexing |
Keyword(4) | Speaker recognition |
Keyword(5) | Speech recognition |
Keyword(6) | Discussions |
1st Author's Name | Masafumi NISHIDA |
1st Author's Affiliation | Graduate School of Science ant Technology, Chiba University() |
2nd Author's Name | Tatsuya KAWAHARA |
2nd Author's Affiliation | School of Informatics, Kyoto University:PRESTO, Japan Science and Technology Corporation (JST) |
Date | 2003/10/24 |
Paper # | SP2003-103,WIT2003-15 |
Volume (vol) | vol.103 |
Number (no) | 402 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |