Presentation | 2005/12/15 Utterance-based Selective Training for Task-Dependent Acoustic Modeling Tobias CINCAREK, Tomoki TODA, Hiroshi SARUWATARI, Kiyohiro SHIKANO, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Large amounts of speech data are necessary to construct high performance acoustic models. Since speech recognition performance is task-dependent and the effort and costs for speech data collection and transcription are very high, it is infeasable to prepare enough data for every new application which makes use of speech recognition technology. In this paper an algorithm for utterance-based selective training is proposed, which enables the automatic and cost-effective construction of task-dependent acoustic models. Training utterances are selected from existing speech data resources so that the likelihood of an independent development data set is maximized. Fast calculation of the likelihood is possible with sufficient statistics. The algorithm is evaluated for constructing an infant-dependent model with speech from elementary school children and an elderly-dependent model with adult speech data. Selective training is already effective with only ten development utterances. Furthermore, a higher word accuracy than with the standard adaptation methods MAP and MLLR was achieved. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Acoustic Modeling / Task-Dependency / Cost Reduction / Selective Training / Sufficient Statistics |
Paper # | NLC2005-102,SP2005-135 |
Date of Issue |
Conference Information | |
Committee | NLC |
---|---|
Conference Date | 2005/12/15(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 | 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) | Utterance-based Selective Training for Task-Dependent Acoustic Modeling |
Sub Title (in English) | |
Keyword(1) | Acoustic Modeling |
Keyword(2) | Task-Dependency |
Keyword(3) | Cost Reduction |
Keyword(4) | Selective Training |
Keyword(5) | Sufficient Statistics |
1st Author's Name | Tobias CINCAREK |
1st Author's Affiliation | Nara Institute of Science and Technology() |
2nd Author's Name | Tomoki TODA |
2nd Author's Affiliation | Nara Institute of Science and Technology |
3rd Author's Name | Hiroshi SARUWATARI |
3rd Author's Affiliation | Nara Institute of Science and Technology |
4th Author's Name | Kiyohiro SHIKANO |
4th Author's Affiliation | Nara Institute of Science and Technology |
Date | 2005/12/15 |
Paper # | NLC2005-102,SP2005-135 |
Volume (vol) | vol.105 |
Number (no) | 494 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |