Presentation | 2000/1/21 Metatopic foreseeing and the Synthesis Generation Corresponded with it in Voice Dialogue System Kazuhide Okada, Yasuo Horiuchi, Akira Ichikawa, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Looking at continuous conversation, we can say that we have the different two topics shortly (1) SuperTopic which has been separated by "Well" in Japanese or long pause in which speakers try to attend some conclusion each other and (2) MetaTopic which has been separated as several parts which compose the process for attending conclusion inside SuperTopic It means that in natural dialogue except when a speaker encounter an urgent situation or when they have a rivalry for each opinion, both speakers co-operate to form one conclusion conserning one SuperTopic and at the timingg in which the said conclusion had been formed, they logically jump into the next SuperTopic and let the operation for attending the newconclusion start. We propose an algorithm for the Artificial Voice Dialogue System which can raise the recognition ratio for sentenses over all, by using the Status Transfer Probability Table. For a Table which embraces the probability by which the control is moved from the previous sentense into the next one, we make the forecast for the next metatopic as the middle process for forming SuperTopic possible and supplement the unrecognized part for Voice Recognition System considering the poverty for the present Language Model, rather building the Voice DialogueSystem for which phoneme analysis has been mainly made much of. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | MetaTopic / SuperTopic / Status Transfer Probability Table |
Paper # | SP99-146 |
Date of Issue |
Conference Information | |
Committee | SP |
---|---|
Conference Date | 2000/1/21(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 | Speech (SP) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Metatopic foreseeing and the Synthesis Generation Corresponded with it in Voice Dialogue System |
Sub Title (in English) | |
Keyword(1) | MetaTopic |
Keyword(2) | SuperTopic |
Keyword(3) | Status Transfer Probability Table |
1st Author's Name | Kazuhide Okada |
1st Author's Affiliation | Intelligentnce and Information Lab., Graduate School of Science and Technology, Chiba University() |
2nd Author's Name | Yasuo Horiuchi |
2nd Author's Affiliation | Intelligentnce and Information Lab., Graduate School of Science and Technology, Chiba University |
3rd Author's Name | Akira Ichikawa |
3rd Author's Affiliation | Intelligentnce and Information Lab., Graduate School of Science and Technology, Chiba University |
Date | 2000/1/21 |
Paper # | SP99-146 |
Volume (vol) | vol.99 |
Number (no) | 577 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |