| Presentation | 2002/12/12 Acoustic modeling using word contexts for spontaneous speech recognition Kenzo ISOGAWA, Koichi SHINODA, Shigeki SAGAYAMA, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, we study state clustering using word contexts for speech recognition. In spontaneous speech, poorly articulated words often cause recognition error. To improve the recognition performance, we add two questions used in the phonetical decision tree based state clustering. One is a question about parts of speech, and the other is a question about the position of phones within a word. To apply the question about parts of speech, we classify parts of speech into two classes based on the word's duration estimated by using the corpus of spontaneous speech. After making HMMs for each class, we carry out state clustering using a context desicion tree with the questions about the classes. To apply questions about the position of phones within a word, we make HMMs for phones at the beginning of the word, those for phones at the ending of the word, and those for phones at the other positions, separately. Then we carry out state clustering using a context desicion tree with questions about phone positions. We carried out speech recognition experiments using CSJ(Corpus of Spontaneous Japanese). In the best case, the word accuracy improved by 2.4 points with the use of the former method, and it improved by 6.1 points with the use of the latter method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | spontaneous speech / acoustic model / part of speech / decision tree |
| Paper # | SP2002-139 |
| Date of Issue |
| Conference Information | |
| Committee | SP |
|---|---|
| Conference Date | 2002/12/12(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) | Acoustic modeling using word contexts for spontaneous speech recognition |
| Sub Title (in English) | |
| Keyword(1) | spontaneous speech |
| Keyword(2) | acoustic model |
| Keyword(3) | part of speech |
| Keyword(4) | decision tree |
| 1st Author's Name | Kenzo ISOGAWA |
| 1st Author's Affiliation | Graduate School of Information Science and Technology, The University of Tokyo() |
| 2nd Author's Name | Koichi SHINODA |
| 2nd Author's Affiliation | Graduate School of Information Science and Technology, The University of Tokyo |
| 3rd Author's Name | Shigeki SAGAYAMA |
| 3rd Author's Affiliation | Graduate School of Information Science and Technology, The University of Tokyo |
| Date | 2002/12/12 |
| Paper # | SP2002-139 |
| Volume (vol) | vol.102 |
| Number (no) | 529 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |