Presentation | 2009-01-29 Speeding up fundamental frequency information extraction by Hough transform for noise-robust speech recognition Hideki YASUI, Koichi SHINODA, Sadaoki FURUI, Koji IWANO, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | While F_0 information obtained by Hough transform has been shown to be effective in speech recognition in noisy environment, it is difficult to use in real time applications because the computational costs for Hough transform is relatively high. This paper proposes an efficient F_0 extraction method using Hough transform. The number of frames perfoming Hough transform is reduced by reusing the voting values on the m-c plane calculated in the previous frames. We performed the evaluation experiments using the Japanese Newspaper Article Sentences and the JEIDA-NOISE database. Improvement of word accuracy on average over all the noise conditions was 1.5 points. In comparison with our previous study, computational costs for F_0 extraction was reduced by 44.7%. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Hough transform / fundamental frequency information / speeding up / spectral subtraction / noise robust speech recognition |
Paper # | SP2008-129 |
Date of Issue |
Conference Information | |
Committee | SP |
---|---|
Conference Date | 2009/1/22(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) | Speeding up fundamental frequency information extraction by Hough transform for noise-robust speech recognition |
Sub Title (in English) | |
Keyword(1) | Hough transform |
Keyword(2) | fundamental frequency information |
Keyword(3) | speeding up |
Keyword(4) | spectral subtraction |
Keyword(5) | noise robust speech recognition |
1st Author's Name | Hideki YASUI |
1st Author's Affiliation | Department of Computer Science, Tokyo Institute of Technology() |
2nd Author's Name | Koichi SHINODA |
2nd Author's Affiliation | Department of Computer Science, Tokyo Institute of Technology |
3rd Author's Name | Sadaoki FURUI |
3rd Author's Affiliation | Department of Computer Science, Tokyo Institute of Technology |
4th Author's Name | Koji IWANO |
4th Author's Affiliation | Faculty of Environmental and Information Studies, Musashi Institute of Technology |
Date | 2009-01-29 |
Paper # | SP2008-129 |
Volume (vol) | vol.108 |
Number (no) | 422 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |