| Presentation | 2022-03-02 Evaluation of sentence-level generation in Japanese dialect speech synthesis using accent latent variables Kazuya Yufune, Tomoki Koriyama, Shinnosuke Takamichi, Hiroshi Saruwatari, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Japanese dialect speech synthesis is useful for personalized speech synthesis systems. However, inability to prepare accent labels is an obstacle to improving the naturalness of the synthesized dialectal speeches. In the past, we proposed an accent-label-free method to model the pitch accent of Japanese dialects as mora-level accent latent variables (ALVs) using vector quantized variational autoencoder (VQ-VAE), and we evaluated its performance for phrase-level utterances. In this paper, we apply the same method with some modifications to sentence-level dialectal utterances and evaluate it. The experimental evaluation showed that the ALVs can be used to model the pitch accent even of sentence-level utterances, that the proposed method can synthesize more natural pitch accents from text than the conventional one when the text analysis is accurate, and that the proposed method improves the controllability of synthesized pitch accents. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Dialect speech synthesis / accent latent variable / VQ-VAE / pitch accent / latent variable |
| Paper # | EA2021-79,SIP2021-106,SP2021-64 |
| Date of Issue | 2022-02-22 (EA, SIP, SP) |
| Conference Information | |
| Committee | EA / SIP / SP / IPSJ-SLP |
|---|---|
| Conference Date | 2022/3/1(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Yoshinobu Kajikawa(Kansai Univ.) / Yukihiro Bandou(NTT) / Norihide Kitaoka(Toyohashi Univ. of Tec) / 北岡 教英(豊橋技科大) |
| Vice Chair | Kenichi Furuya(Oita Univ.) / Shoichi Koyama(Univ. of Tokyo) / Toshihisa Tanaka(Tokyo Univ. Agri.&Tech.) / Takayuki Nakachi(Ryukyu Univ.) |
| Secretary | Kenichi Furuya(NTT) / Shoichi Koyama(RitsumeikanUniv.) / Toshihisa Tanaka(Xiaomi) / Takayuki Nakachi(Takushoku Univ.) / (Tokyo Univ. Agri.&Tech.) / (Univ. of Tokyo) |
| Assistant | Yukou Wakabayashi(Tokyo Metropolitan Univ.) / Tatsuya Komatsu(LINE) / Taichi Yoshida(UEC) / Seisuke Kyochi(Univ. of Kitakyushu) / Toru Nakashika(Univ. of Electro-Comm.) / Ryo Masumura(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Engineering Acoustics / Technical Committee on Signal Processing / Technical Committee on Speech / 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) | Evaluation of sentence-level generation in Japanese dialect speech synthesis using accent latent variables |
| Sub Title (in English) | |
| Keyword(1) | Dialect speech synthesis |
| Keyword(2) | accent latent variable |
| Keyword(3) | VQ-VAE |
| Keyword(4) | pitch accent |
| Keyword(5) | latent variable |
| 1st Author's Name | Kazuya Yufune |
| 1st Author's Affiliation | the University of Tokyo(UTokyo) |
| 2nd Author's Name | Tomoki Koriyama |
| 2nd Author's Affiliation | the University of Tokyo(UTokyo) |
| 3rd Author's Name | Shinnosuke Takamichi |
| 3rd Author's Affiliation | the University of Tokyo(UTokyo) |
| 4th Author's Name | Hiroshi Saruwatari |
| 4th Author's Affiliation | the University of Tokyo(UTokyo) |
| Date | 2022-03-02 |
| Paper # | EA2021-79,SIP2021-106,SP2021-64 |
| Volume (vol) | vol.121 |
| Number (no) | EA-383,SIP-384,SP-385 |
| Page | pp.pp.96-101(EA), pp.96-101(SIP), pp.96-101(SP), |
| #Pages | 6 |
| Date of Issue | 2022-02-22 (EA, SIP, SP) |