HMM-based speech synthesis with unsupervised labeling of accentual context based on F0 quantization and average voice model
- 1 January 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 4622-4625
Abstract
This paper proposes an HMM-based speech synthesis technique without any manual labeling of accent information for a target speaker's training data. To appropriately model the fundamental frequency (F0) feature of speech, the proposed technique uses coarsely quantized F0 symbols instead of accent types for the context-dependent labeling. By using F0 quantization, we can automatically conduct the labeling of F0 contexts for training data. When synthesizing speech, an average voice model trained in advance using manually labeled multiple speakers' speech data including accent information is used to create the label sequence for synthesis. Specifically, the input text is converted to a full context label sequence, and an F0 contour is generated from the label sequence and the average voice model. Then, a label sequence including the quantized F0 symbols is created from the generated F0 contour. We conduct objective and subjective evaluation tests, and discuss the results.Keywords
This publication has 8 references indexed in Scilit:
- Two-pass decision tree construction for unsupervised adaptation of HMM-based synthesis models2009
- Unsupervised adaptation for HMM-based speech synthesis2008
- Voice Conversion Based on Maximum-Likelihood Estimation of Spectral Parameter TrajectoryIEEE Transactions on Audio, Speech, and Language Processing, 2007
- A Hidden Semi-Markov Model-Based Speech Synthesis SystemIEICE Transactions on Information and Systems, 2007
- A Speaker Adaptation Technique for MRHSMM-Based Style Control of Synthetic Speech2007
- Acoustic Modeling of Speaking Styles and Emotional Expressions in HMM-Based Speech SynthesisIEICE Transactions on Information and Systems, 2005
- Text-to-speech synthesis with arbitrary speaker's voice from average voice2001
- Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis1999