| Presentation | 1994/7/22 Parameter Extraction of Speech under Noisy Environment Using a Digital Cochlear Model Makoto Iwata, Tsuyoshi Usagawa, Masanao Ebata, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Surrounding noise is one of the most serious problems to realize a speech recognition system.Because noise affects the performance even if its level is low.On the other hand,human being can easily recognize what speech means when noise has comparable level with speech.This means the human auditory system has some mochanisms to reduce the effect of noise.We have used masking model based on psychophysical experiments,as a front-end of speech recognition system which simulates voice controller of television set.In this paper,we propose a new parameter extraction method using a digital cochlear model instead of masking model.The model consists of the middle ear and the mechanical motion of the cochlea.The experiments are carried out on condition that the proposed method is implemented in the voice controller of television set. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | speech recognition in noisy environment / masking model / digital cochlear model / voice controller of television set |
| Paper # | SP94-33 |
| Date of Issue |
| Conference Information | |
| Committee | SP |
|---|---|
| Conference Date | 1994/7/22(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) | Parameter Extraction of Speech under Noisy Environment Using a Digital Cochlear Model |
| Sub Title (in English) | |
| Keyword(1) | speech recognition in noisy environment |
| Keyword(2) | masking model |
| Keyword(3) | digital cochlear model |
| Keyword(4) | voice controller of television set |
| 1st Author's Name | Makoto Iwata |
| 1st Author's Affiliation | Depertment of Electrical Engineering and Computer Science,Faculty of Engineering,Kumamoto University() |
| 2nd Author's Name | Tsuyoshi Usagawa |
| 2nd Author's Affiliation | Depertment of Electrical Engineering and Computer Science,Faculty of Engineering,Kumamoto University |
| 3rd Author's Name | Masanao Ebata |
| 3rd Author's Affiliation | Depertment of Electrical Engineering and Computer Science,Faculty of Engineering,Kumamoto University |
| Date | 1994/7/22 |
| Paper # | SP94-33 |
| Volume (vol) | vol.94 |
| Number (no) | 166 |
| Page | pp.pp.- |
| #Pages | 7 |
| Date of Issue | |