| Presentation | 2017-12-22 [Invited Talk] Expressive Speech Synthesis: Approaches to Text-to-Speech with Diverse Voices and Styles Takao Kobayashi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | As the performance of smart devices and information systems becomes higher, more advanced speech interfaces are requested to make such devices and systems human-friendly. Regarding speech output in spoken language interface, which is based on text-to-speech technique, synthetic speech should be not only natural sounding but also expressive. This talk gives an overview of approaches to synthesizing speech with diverse voice characteristics and speaking styles and/or emotional expressions based on a statistical parametric speech synthesis framework. Recent advances in expressive speech synthesis studies will be also presented. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | text-to-speech / statistical parametric speech synthesis / HMM-based speech synthesis / average-voice-based speech synthesis / style adaptation / style control |
| Paper # | SP2017-64 |
| Date of Issue | 2017-12-14 (SP) |
| Conference Information | |
| Committee | NLC / IPSJ-NL / SP / IPSJ-SLP |
|---|---|
| Conference Date | 2017/12/20(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Waseda Univ. Green Computing Systems Research Organization |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | The 4th Natural Language Processing Symposium & The 19th Spoken Language Symposium |
| Chair | Hiroshi Kanayama(IBM) / Kentaro Inui(Tohoku Univ.) / Yoichi Yamashita(Ritsumeikan Univ.) / Nobuaki Minematsu(Univ. Tokyo) |
| Vice Chair | Takeshi Sakaki(Hottolink) / Kazutaka Shimada(Kyushu Inst. of Tech.) / / Hiroki Mori(Utsunomiya Univ.) |
| Secretary | Takeshi Sakaki(Ryukoku Univ.) / Kazutaka Shimada(NTT) / (Osaka Univ.) / Hiroki Mori(Tokyo Inst. of Tech.) / (Mixi Co. Ltd.) |
| Assistant | Mitsuo Yoshida(Toyohashi Univ. of Tech.) / Takeshi Kobayakawa(NICT) / / Kei Hashimoto(Nagoya Inst. of Tech.) / Satoshi Kobashikawa(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Natural Language Understanding and Models of Communication / Special Interest Group on Natural Language / 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) | [Invited Talk] Expressive Speech Synthesis: Approaches to Text-to-Speech with Diverse Voices and Styles |
| Sub Title (in English) | |
| Keyword(1) | text-to-speech |
| Keyword(2) | statistical parametric speech synthesis |
| Keyword(3) | HMM-based speech synthesis |
| Keyword(4) | average-voice-based speech synthesis |
| Keyword(5) | style adaptation |
| Keyword(6) | style control |
| 1st Author's Name | Takao Kobayashi |
| 1st Author's Affiliation | Tokyo Institute of Technology(Tokyo Tech.) |
| Date | 2017-12-22 |
| Paper # | SP2017-64 |
| Volume (vol) | vol.117 |
| Number (no) | SP-368 |
| Page | pp.pp.85-86(SP), |
| #Pages | 2 |
| Date of Issue | 2017-12-14 (SP) |