| Presentation | 2014-09-11 Effect of Voice Quality on Theatrical Speech Synthesis Takuya NAKASHIMA, Hiroaki CHISHIMA, Wataru SAKAMOTO, Kenko OTA, Ken'ya JINNO, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This study investigates the spectral band related to the change of voice quality of delighted voices and also the degree of contribution of the voice quality to the delighted voice synthesis quality. Sample voices gathered from the Internet are classified by the degree of delight by a subjective evaluation. As a result of analysis of classified voice data, fundamental frequency and also spectral centroid are getting higher according to the increase in degree of delight. Moreover, power ratio of delighted voices to ordinary voices is high around 4000Hz frequency band. Subjective evaluation using Sheffe's paired comparison is carried out in order to investigate the degree of contribution of above-mentioned features to the delighted voice synthesis quality. As a result, the voice generated by changing the fundamental frequency and spectral centroid is slightly preferable to the voice generated by changing only the fundamental frequency. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Speech synthesis / Synthesis quality / Emotional speech / Theatrical features / Spectral centroid |
| Paper # | CQ2014-51 |
| Date of Issue |
| Conference Information | |
| Committee | CQ |
|---|---|
| Conference Date | 2014/9/4(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 | Communication Quality (CQ) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Effect of Voice Quality on Theatrical Speech Synthesis |
| Sub Title (in English) | |
| Keyword(1) | Speech synthesis |
| Keyword(2) | Synthesis quality |
| Keyword(3) | Emotional speech |
| Keyword(4) | Theatrical features |
| Keyword(5) | Spectral centroid |
| 1st Author's Name | Takuya NAKASHIMA |
| 1st Author's Affiliation | Electronics Information and Media Major Graduate School of Nippon Institute of Technology() |
| 2nd Author's Name | Hiroaki CHISHIMA |
| 2nd Author's Affiliation | Faculty of Engineering Nippon Institute of Technology |
| 3rd Author's Name | Wataru SAKAMOTO |
| 3rd Author's Affiliation | Faculty of Engineering Nippon Institute of Technology |
| 4th Author's Name | Kenko OTA |
| 4th Author's Affiliation | Faculty of Engineering Nippon Institute of Technology |
| 5th Author's Name | Ken'ya JINNO |
| 5th Author's Affiliation | Faculty of Engineering Nippon Institute of Technology |
| Date | 2014-09-11 |
| Paper # | CQ2014-51 |
| Volume (vol) | vol.114 |
| Number (no) | 209 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |