Presentation | 2021-03-03 An investigation of rhythm-based speaker embeddings for phoneme duration modeling Kenichi Fujita, Atsushi Ando, Yusuke Ijima, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this study, we propose a speaker embedding method suitable for modeling phoneme duration length for each individual in speech synthesis. Conventional methods for generating speaker embedding vectors, such as x-vector and i-vector, use spectral features such as mel spectrograms. However, spectral features do not clearly include temporal features such as speech rhythms. Therefore, those vectors can discard individual speech rhythms. In this paper, we propose a method for generating speaker embedding vectors based on temporal features using phonemes and their durations. From the results of speaker recognition experiments and speaker vector distributions, we show that the proposed method shows a certain degree of accuracy in speaker recognition and that similar speaker embedding vectors are generated from speakers with similar phoneme durations. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | speaker embedding / phoneme duration / speech synthesis / speaking rhythm |
Paper # | EA2020-77,SIP2020-108,SP2020-42 |
Date of Issue | 2021-02-24 (EA, SIP, SP) |
Conference Information | |
Committee | EA / US / SP / SIP / IPSJ-SLP |
---|---|
Conference Date | 2021/3/3(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Speech, Engineering/Electro Acoustics, Signal Processing, Ultrasonics, and Related Topics |
Chair | Kenichi Furuya(Oita Univ.) / Hikaru Miura(Nihon Univ.) / Hisashi Kawai(NICT) / Kazunori Hayashi(Kyoto Univ.) / 北岡 教英(豊橋技科大) |
Vice Chair | Yoshinobu Kajikawa(Kansai Univ.) / Kentaro Matsui(NHK) / Jun Kondo(Shizuoka Univ.) / Yoshikazu Koike(Shibaura Inst. of Tech.) / / Yukihiro Bandou(NTT) / Toshihisa Tanaka(Tokyo Univ. Agri.&Tech.) |
Secretary | Yoshinobu Kajikawa(Univ. of Tokyo) / Kentaro Matsui(NTT) / Jun Kondo(Doshisha Univ.) / Yoshikazu Koike(Tohoku Univ.) / (Univ. of Tokyo) / Yukihiro Bandou(Waseda Univ.) / Toshihisa Tanaka(Hosei Univ.) / (Waseda Univ.) |
Assistant | Yukou Wakabayashi(Tokyo Metropolitan Univ.) / Tatsuya Komatsu(LINE) / Shinnosuke Hirata(Tokyo Inst. of Tech.) / Yusuke Ijima(NTT) / Yuichi Tanaka(Tokyo Univ. Agri.&Tech.) |
Paper Information | |
Registration To | Technical Committee on Engineering Acoustics / Technical Committee on Ultrasonics / Technical Committee on Speech / Technical Committee on Signal Processing / Special Interest Group on Spoken Language Processing |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | An investigation of rhythm-based speaker embeddings for phoneme duration modeling |
Sub Title (in English) | |
Keyword(1) | speaker embedding |
Keyword(2) | phoneme duration |
Keyword(3) | speech synthesis |
Keyword(4) | speaking rhythm |
1st Author's Name | Kenichi Fujita |
1st Author's Affiliation | Nippon Telegraph and Telephone corporation(NTT) |
2nd Author's Name | Atsushi Ando |
2nd Author's Affiliation | Nippon Telegraph and Telephone corporation(NTT) |
3rd Author's Name | Yusuke Ijima |
3rd Author's Affiliation | Nippon Telegraph and Telephone corporation(NTT) |
Date | 2021-03-03 |
Paper # | EA2020-77,SIP2020-108,SP2020-42 |
Volume (vol) | vol.120 |
Number (no) | EA-397,SIP-398,SP-399 |
Page | pp.pp.103-108(EA), pp.103-108(SIP), pp.103-108(SP), |
#Pages | 6 |
Date of Issue | 2021-02-24 (EA, SIP, SP) |