Presentation | 2013-01-31 Speaker and Style Diversification in Statistical Parametric Speech Synthesis Takashi NOSE, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper reviews representative techniques for adding and modifying various speaker characteristics and style expressivity to synthetic speech in HMM-based speech synthesis. In the HMM-based speech synthesis, all spectral and prosodic features are parametrized through the modeling and synthesis processes, and hence it is relatively easy to modify model parameters or extend model structure itself. This is one of the reasons that a variety of techniques have been proposed for the purpose of the diversification of synthetic speech. For the speaker characteristics diversification, speaker adaptation, speaker interpolation, and speaker characteristics emphasis are introduced. Another important issue is style diversification, and style modeling, style adaptation, style interpolation, style control, and style conversion techniques are briefly explained. In addition, an overview of the other types of diversification is shown, e.g., voice quality control and spontaneous speech synthesis. Finally, the current problems for this topic and prospect for the future work are given as the conclusions. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | HMM-based speech synthesis / various speaker characteristics / various emotional expressions and speaking styles / voice quality control / spontaneous speech synthesis |
Paper # | SP2012-109 |
Date of Issue |
Conference Information | |
Committee | SP |
---|---|
Conference Date | 2013/1/23(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) | Speaker and Style Diversification in Statistical Parametric Speech Synthesis |
Sub Title (in English) | |
Keyword(1) | HMM-based speech synthesis |
Keyword(2) | various speaker characteristics |
Keyword(3) | various emotional expressions and speaking styles |
Keyword(4) | voice quality control |
Keyword(5) | spontaneous speech synthesis |
1st Author's Name | Takashi NOSE |
1st Author's Affiliation | Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology() |
Date | 2013-01-31 |
Paper # | SP2012-109 |
Volume (vol) | vol.112 |
Number (no) | 422 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |