Presentation | 2008-12-10 Speech recognition system for spoken dialogue system Toru TANIGUCHI, Shinya FUJIE, Tetsunori KOBAYASHI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We have developed speech recognition method for spoken dialogue systems such as communication robots. In the case of development of spoken dialogue systems, grammar-based speech recognizers are desirable rather than n-gram based ones because of the ease of dialogue design. However, there are problems of the recognizers that out-of-grammar utterances cause recognition errors and that the performance of the recognizer declines if the size of the grammar increases. Furthermore, fragmentation of a spoken sentence occurs because of unfilled pause in the sentence and errors by voice activity detection. To overcome these problems, multi-decoding using multiple grammars, the rejection method of out-of-grammar utterances, and the recognition method with integration of fragmentary spoken sentences has been realized. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | spoken dialogue system / speech recognition / multi-decoding / voice activity detection / fragmented utterance |
Paper # | NLC2008-41,SP2008-96 |
Date of Issue |
Conference Information | |
Committee | NLC |
---|---|
Conference Date | 2008/12/2(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) | Speech recognition system for spoken dialogue system |
Sub Title (in English) | |
Keyword(1) | spoken dialogue system |
Keyword(2) | speech recognition |
Keyword(3) | multi-decoding |
Keyword(4) | voice activity detection |
Keyword(5) | fragmented utterance |
1st Author's Name | Toru TANIGUCHI |
1st Author's Affiliation | Department of Computer Science and Engineering, Waseda University() |
2nd Author's Name | Shinya FUJIE |
2nd Author's Affiliation | Waseda Institute for Advanced Study, Waseda University |
3rd Author's Name | Tetsunori KOBAYASHI |
3rd Author's Affiliation | Department of Computer Science and Engineering, Waseda University |
Date | 2008-12-10 |
Paper # | NLC2008-41,SP2008-96 |
Volume (vol) | vol.108 |
Number (no) | 337 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |