Presentation | 2004/12/15 Spoken Dialogue System Using Utterance Prediction Masafumi NISHIDA, Hiromasa TERASHI, Yasuo HORIUCHI, Akira ICHIKAWA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We have already proposed a speech recognition method using prediction for spontaneous speech. In this study, we construct a spoken dialogue system based on the proposed method. The system performs the speech recognition using prediction and large vocabulary continuous speech recognition (LVCSR) and can detect whether the prediction is correct by comparing these recognition likelihoods. Furthermore, we propose a dialogue control method using the recognition likelihoods and confidence measure based on the recognition results. We applied the proposed method to the spoken dialogue system and conducted experiments. As a result, a speech recognition accuracy was 92.3 % and prediction accuracy was 97 % by the speech recognition method using prediction. The number of user utterance decreased by the dialogue control method using prediction and confidence measure. Therefore, the proposed method was effective and the system was able to achieve the flexible dialogue. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Utterance prediction / Confidence measure / Speech recognition / Dialogue control / Spoken dialogue system |
Paper # | NLC2004-92,SP2004-132 |
Date of Issue |
Conference Information | |
Committee | NLC |
---|---|
Conference Date | 2004/12/15(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) | Spoken Dialogue System Using Utterance Prediction |
Sub Title (in English) | |
Keyword(1) | Utterance prediction |
Keyword(2) | Confidence measure |
Keyword(3) | Speech recognition |
Keyword(4) | Dialogue control |
Keyword(5) | Spoken dialogue system |
1st Author's Name | Masafumi NISHIDA |
1st Author's Affiliation | Department of Information and Image Science, Faculty of Engineering, Chiba University() |
2nd Author's Name | Hiromasa TERASHI |
2nd Author's Affiliation | Department of Information and Image Science, Faculty of Engineering, Chiba University |
3rd Author's Name | Yasuo HORIUCHI |
3rd Author's Affiliation | Department of Information and Image Science, Faculty of Engineering, Chiba University |
4th Author's Name | Akira ICHIKAWA |
4th Author's Affiliation | Department of Information and Image Science, Faculty of Engineering, Chiba University |
Date | 2004/12/15 |
Paper # | NLC2004-92,SP2004-132 |
Volume (vol) | vol.104 |
Number (no) | 540 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |