| Presentation | 2002/12/12 A Study on Robust Speech Recognition by Using Distinctive Phonetic Feature Vectors Takashi FUKUDA, Wataru YAMAMOTO, Tsuneo NITTA, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper describes an attempt to extract distinctive phonetic features (DPFs) that represent articulatory gestures in linguistic theory by using a multi-layer neural network (MLN) and to apply the DPFs to noise-robust speech recognition. In the DPF extraction stage, after converting a speech signal to acoustic features composed of local features (LFs), an MLN with 33 output units corresponding to context-dependent DPFs of 11 DPFs, 11 preceding context DPFs, and 11 following context DPFs maps the LFs to DPFs. In experiments, firstly, the configuration of MLN output units is compared. The proposed DPF parameters without MFCC were secondly evaluated in comparison with a standard parameter set of MFCC and dynamic features on a word recognition task using clean speech and the result showed the same performance as that of the standard set. Noise robustness of these parameters was then tested with four types of additive noise and the proposed DPF parameters outperformed the standard set except one additive noise type. The combinatorial usage of DPFs and MFCC is also tested. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | robust speech recognition / feature extraction / distinctive phonetic feature / multi-layer neural network / local feature |
| Paper # | NLC2002-44 |
| Date of Issue |
| Conference Information | |
| Committee | NLC |
|---|---|
| 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 | 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) | A Study on Robust Speech Recognition by Using Distinctive Phonetic Feature Vectors |
| Sub Title (in English) | |
| Keyword(1) | robust speech recognition |
| Keyword(2) | feature extraction |
| Keyword(3) | distinctive phonetic feature |
| Keyword(4) | multi-layer neural network |
| Keyword(5) | local feature |
| 1st Author's Name | Takashi FUKUDA |
| 1st Author's Affiliation | Graduate School of Engineering, Toyohashi University of Technology() |
| 2nd Author's Name | Wataru YAMAMOTO |
| 2nd Author's Affiliation | Graduate School of Engineering, Toyohashi University of Technology |
| 3rd Author's Name | Tsuneo NITTA |
| 3rd Author's Affiliation | Graduate School of Engineering, Toyohashi University of Technology |
| Date | 2002/12/12 |
| Paper # | NLC2002-44 |
| Volume (vol) | vol.102 |
| Number (no) | 527 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |