Presentation | 1999/2/19 A simple method of phoneme segmentation for detection of local speech rate variation and its application to speech data recorded in real environment Junichi Sasaki, Makoto Hiroshige, Yoshikazu Miyanaga, Koji Tochinai, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this report, a simple method of phoneme segmentation for detection of local speech rate variation is described. It is said that Japanese speech contains less variation of speech rate than other languages. Thus if there is a large variation of speech rate, such portion of speech may contain speaker's strong intention. The speech rate obtained with this method is expected to supply useful information to speech recognition system, recognition error correction system, or speech understanding system. In this report, we express speech rate variation by calculating the number of phoneme changes within a particular time a duration that is selected to easily express speaker's intention. Spontaneous speech data which may contain large amount of rate variation are recorded in real environment. The results of rate detection experiments for the recorded speech data are described. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Speech rate variation / Prosodic infomation / Phoneme segmentation / Speech data in real environment |
Paper # | SP98-142 |
Date of Issue |
Conference Information | |
Committee | SP |
---|---|
Conference Date | 1999/2/19(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) | A simple method of phoneme segmentation for detection of local speech rate variation and its application to speech data recorded in real environment |
Sub Title (in English) | |
Keyword(1) | Speech rate variation |
Keyword(2) | Prosodic infomation |
Keyword(3) | Phoneme segmentation |
Keyword(4) | Speech data in real environment |
1st Author's Name | Junichi Sasaki |
1st Author's Affiliation | Department of Engineering Hokkaido University() |
2nd Author's Name | Makoto Hiroshige |
2nd Author's Affiliation | Department of Engineering Hokkaido University |
3rd Author's Name | Yoshikazu Miyanaga |
3rd Author's Affiliation | Department of Engineering Hokkaido University |
4th Author's Name | Koji Tochinai |
4th Author's Affiliation | Department of Engineering Hokkaido University |
Date | 1999/2/19 |
Paper # | SP98-142 |
Volume (vol) | vol.98 |
Number (no) | 611 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |