Speaker-independent style conversion for HMM-based expressive speech synthesis
- 1 May 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 7864-7868
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
This publication has 12 references indexed in Scilit:
- Data-driven emotion conversion in spoken EnglishSpeech Communication, 2009
- Analysis of Speaker Adaptation Algorithms for HMM-Based Speech Synthesis and a Constrained SMAPLR Adaptation AlgorithmIEEE Transactions on Audio, Speech, and Language Processing, 2009
- A Hidden Semi-Markov Model-Based Speech Synthesis SystemIEICE Transactions on Information and Systems, 2007
- A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech SynthesisIEICE Transactions on Information and Systems, 2007
- Average-Voice-Based Speech Synthesis Using HSMM-Based Speaker Adaptation and Adaptive TrainingIEICE Transactions on Information and Systems, 2007
- A Style Adaptation Technique for Speech Synthesis Using HSMM and Suprasegmental FeaturesIEICE Transactions on Information and Systems, 2006
- A compact model for speaker-adaptive training2002
- Structural maximum a posteriori linear regression for fast HMM adaptationComputer Speech & Language, 2002
- Restructuring speech representations using a pitch-adaptive time–frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in soundsSpeech Communication, 1999
- Maximum likelihood linear transformations for HMM-based speech recognitionComputer Speech & Language, 1998