| Presentation | 2002/12/13 Unsupervised batch-type adaptation method for language models Tadasuke YOKOYAMA, Takahiro SHINOZAKI, Koji IWANO, Sadaoki FURUI, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper proposes an unsupervised, batch-type, class-based language model adaptation method for spontaneous speech recognition. The word classes are automatically determined by maximizing the bigram likelihood using a training set. A class-based language model is built based on recognition hypotheses obtained using a general word-based language model, and linearly interpolated with the general language model. All the input utterances are re-recognized using the adapted language model. The proposed method was applied to the recognition of spontaneous presentations and was found to be effective in improving the recognition accuracy for all the presentations. The best condition was found to be using 100 word classes, and in this condition 2.3% of the absolute value improvement in the word accuracy averaged over all the speakers was achieved, using speaker independent acoustic models. It was also found that effectiveness of the proposed method is additive to that of the acoustic model adaptation. Consequently, 71.8% word recognition accuracy was achieved for spontaneous presentations after adapting both acoustic and language models. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Unsupervised language model adaptation / batch-type adaptation / class-based language model |
| Paper # | NLC2002-74 |
| Date of Issue |
| Conference Information | |
| Committee | NLC |
|---|---|
| Conference Date | 2002/12/13(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) | Unsupervised batch-type adaptation method for language models |
| Sub Title (in English) | |
| Keyword(1) | Unsupervised language model adaptation |
| Keyword(2) | batch-type adaptation |
| Keyword(3) | class-based language model |
| 1st Author's Name | Tadasuke YOKOYAMA |
| 1st Author's Affiliation | Department of Computer Science, Tokyo Institute of Technology() |
| 2nd Author's Name | Takahiro SHINOZAKI |
| 2nd Author's Affiliation | Department of Computer Science, Tokyo Institute of Technology |
| 3rd Author's Name | Koji IWANO |
| 3rd Author's Affiliation | Department of Computer Science, Tokyo Institute of Technology |
| 4th Author's Name | Sadaoki FURUI |
| 4th Author's Affiliation | Department of Computer Science, Tokyo Institute of Technology |
| Date | 2002/12/13 |
| Paper # | NLC2002-74 |
| Volume (vol) | vol.102 |
| Number (no) | 528 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |