| Presentation | 2005/12/15 Task extension with fusion of N-gram and grammar in public speech dialogue system Takahiro KITAMURA, Tomoki TODA, Hiromichi KAWANAMI, Akinobu LEE, Hiroshi SARUWATARI, Kiyohiro SHIKANO, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | A suitable task domain for speech recognition and speech dialogue systems used in a real environment is important. It is indispensable to popularize such systems so that its technology can easily be applied or enhanced to a required task. When a new task is added to an existing speech dialogue system, discrimination of the domain and construction of new dialogue strategy are needed. In using a new statistical language model, a large amount of corpus is needed and it takes much time to produce it. We propose a technique that can add a new task easily by introducing a network grammar to an existing statistical language model-based speech dialogue system. The proposed method can realize domain discrimination and speech recognition with high accuracy. In the experimental evaluation, more than 90% of domain discrimination and word recognition rate are realized. The effectiveness of the proposed technique is confirmed. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | N-gram / Grammar / fusion / spoken dialogue system / Task extension |
| Paper # | NLC2005-74,SP2005-107 |
| 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) | Task extension with fusion of N-gram and grammar in public speech dialogue system |
| Sub Title (in English) | |
| Keyword(1) | N-gram |
| Keyword(2) | Grammar |
| Keyword(3) | fusion |
| Keyword(4) | spoken dialogue system |
| Keyword(5) | Task extension |
| 1st Author's Name | Takahiro KITAMURA |
| 1st Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology() |
| 2nd Author's Name | Tomoki TODA |
| 2nd Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology |
| 3rd Author's Name | Hiromichi KAWANAMI |
| 3rd Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology |
| 4th Author's Name | Akinobu LEE |
| 4th Author's Affiliation | Department of Computer Science and Engineering, Nagoya Institute of Technology |
| 5th Author's Name | Hiroshi SARUWATARI |
| 5th Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology |
| 6th Author's Name | Kiyohiro SHIKANO |
| 6th Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology |
| Date | 2005/12/15 |
| Paper # | NLC2005-74,SP2005-107 |
| Volume (vol) | vol.105 |
| Number (no) | 494 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |