| Presentation | 2002/12/13 Recognition of Spontaneous Speech by Using a General-Purpose LVCSR with 0-gram and Distinctive Phonetic Features Shingo ISEJI, Takashi FUKUDA, Kouichi KATSURADA, Tsuneo NITTA, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper describes an attempt to recognize spontaneously spoken dialogue by using a general-purpose LVCSR software. In the proposed method, a phoneme string output from the LVCSR is converted into a sequence of vectors represented with distinctive phonetic features, then keywords assigned by a dialogue manager are detected from the input vector sequence. The method takes advantage of the potential abilities of: (1) precise phoneme discrimination achieved by relaxing the linguistic constraint in the LVCSR, and (2) coping with the issued of substitution, deletion and insertion errors by combining a conversion process from a phoneme into a distinctive phonetic feature vector and a key-word spotting process. The proposed method shows significant improvements in comparison with the LVCSR software in an experiment with a spoken dialogue corpus of a map guidance task. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Spoken Dialogue / LVCSR / Keyword Spotting / Language Model / Sub-word Model / Distinctive Phonetic Feature / Confusion Matrix |
| Paper # | NLC2002-79 |
| 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) | Recognition of Spontaneous Speech by Using a General-Purpose LVCSR with 0-gram and Distinctive Phonetic Features |
| Sub Title (in English) | |
| Keyword(1) | Spoken Dialogue |
| Keyword(2) | LVCSR |
| Keyword(3) | Keyword Spotting |
| Keyword(4) | Language Model |
| Keyword(5) | Sub-word Model |
| Keyword(6) | Distinctive Phonetic Feature |
| Keyword(7) | Confusion Matrix |
| 1st Author's Name | Shingo ISEJI |
| 1st Author's Affiliation | Graduate School of Engineering, Toyohashi University of Technology() |
| 2nd Author's Name | Takashi FUKUDA |
| 2nd Author's Affiliation | Graduate School of Engineering, Toyohashi University of Technology |
| 3rd Author's Name | Kouichi KATSURADA |
| 3rd Author's Affiliation | Graduate School of Engineering, Toyohashi University of Technology |
| 4th Author's Name | Tsuneo NITTA |
| 4th Author's Affiliation | Graduate School of Engineering, Toyohashi University of Technology |
| Date | 2002/12/13 |
| Paper # | NLC2002-79 |
| Volume (vol) | vol.102 |
| Number (no) | 528 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |