Presentation | 2005/12/15 Automatic recognition of Japanese vowel sequences in noise using structural representation of speech T. MURAKAMI, K. MARUYAMA, MINEMATSU N. /, K. HIROSE, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Non-linguistic features such as vocal tract shapes and acoustic devices are inevitably involved in speech. Recently, a new representation of speech without any dimensions indicating the non-linguistic features was proposed. It discards the absolute properties of speech events and captures only the interrelations among them. In this paper, first, analysis experiments of the representation in noise were conducted. The results showed that though additive noise distorts the representation, it can remove much of speaker individuality by modifying the upper-band spectrum to be uniform. In the next, recognition experiments of Japanese vowel sequences in noise were done. The results showed that the proposed method trained from a single speaker in the matched condition can outperform the conventional method trained from 4,130 speakers with SS and CMN. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | structural representation of speech / speech recognition / Japanese vowel sequences / additive noise / uniform upper-band spectrum |
Paper # | NLC2005-97,SP2005-130 |
Date of Issue |
Conference Information | |
Committee | NLC |
---|---|
Conference Date | 2005/12/15(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) | Automatic recognition of Japanese vowel sequences in noise using structural representation of speech |
Sub Title (in English) | |
Keyword(1) | structural representation of speech |
Keyword(2) | speech recognition |
Keyword(3) | Japanese vowel sequences |
Keyword(4) | additive noise |
Keyword(5) | uniform upper-band spectrum |
1st Author's Name | T. MURAKAMI |
1st Author's Affiliation | Graduate School of Information Science and Technology, University of Tokyo() |
2nd Author's Name | K. MARUYAMA |
2nd Author's Affiliation | Graduate School of Information Science and Technology, University of Tokyo |
3rd Author's Name | MINEMATSU N. / |
3rd Author's Affiliation | Graduate School of Frontier Sciences, University of Tokyo |
4th Author's Name | K. HIROSE |
4th Author's Affiliation | Graduate School of Frontier Sciences, University of Tokyo |
Date | 2005/12/15 |
Paper # | NLC2005-97,SP2005-130 |
Volume (vol) | vol.105 |
Number (no) | 494 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |