DocumentCode :
1693049
Title :
Speaker-independent style conversion for HMM-based expressive speech synthesis
Author :
Kanagawa, Hiroki ; Nose, Takashi ; Kobayashi, Takehiko
Author_Institution :
Interdiscipl. Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Tokyo, Japan
fYear :
2013
Firstpage :
7864
Lastpage :
7868
Abstract :
This paper proposes a technique for creating target speaker´s expressive-style model from the target speaker´s neutral style speech in HMM-based speech synthesis. The technique is based on the style adaptation using linear transforms where speaker-independent transformation matrices are estimated in advance using pairs of neutral and target-style speech data of multiple speakers. By applying the obtained transformation matrices to a new speaker´s neutral-style model, we can convert the style expressivity of the acoustic model to the target style without preparing any target-style speech of the speaker. In addition, we introduce a speaker adaptive training (SAT) framework into the transform estimation to reduce the acoustic difference among speakers. We subjectively evaluate the performance of the style conversion in terms of the naturalness, speaker similarity, and style reproducibility.
Keywords :
hidden Markov models; speech synthesis; HMM-based expressive speech synthesis; SAT framework; acoustic difference; expressive-style model; linear transforms; multiple speakers; neutral speech data; speaker adaptive training; speaker neutral style speech; speaker-independent style conversion; speaker-independent transformation matrices; target-style speech data; Adaptation models; Estimation; Hidden Markov models; Speech; Speech synthesis; Training; Transforms; HMM-based expressive speech synthesis; linear transform; speaker adaptive training; style adaptation; style conversion;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on
Conference_Location :
Vancouver, BC
ISSN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.2013.6639195
Filename :
6639195
Link To Document :
بازگشت