Factor analyzed voice models for HMM-based speech synthesis

This paper describes factor analyzed voice models for realizing various voice characteristics in the HMM-based speech synthesis. The eigenvoice method can synthesize speech with arbitrary voice characteristics by interpolating representative HMM sets. However, the objective of PCA is to accurately r...

Full description

Saved in:
Bibliographic Details
Main Authors: Kazumi, K, Nankaku, Y, Tokuda, K
Format: Conference Proceeding
Language:English
Subjects:
Algorithm design and analysis
Annealing
Character generation
Decision trees
deterministic annealing EM algorithm
eigenvoice
expectation maximization algorithm
factor analysis
Hidden Markov models
HMM-based speech synthesis
Maximum likelihood estimation
Principal component analysis
Speech analysis
Speech synthesis
Training data
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper describes factor analyzed voice models for realizing various voice characteristics in the HMM-based speech synthesis. The eigenvoice method can synthesize speech with arbitrary voice characteristics by interpolating representative HMM sets. However, the objective of PCA is to accurately reconstruct each speaker-dependent HMM set, and this is not equivalent to estimating models which represent training data accurately. To overcome this problem, we propose a general speech model which generates speech utterances with various voice characteristics directly. In the proposed method, the HMM states, factors representing voice characteristics and contextual decision trees are simultaneously optimized within a unified framework.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2010.5495689