Context adaptive training with factorized decision trees for HMM-based statistical parametric speech synthesis

Authors:
Kai Yu;Heiga Zen;François Mairesse;Steve Young
Affiliations:
Machine Intelligence Lab, Cambridge University Engineering Department, Cambridge CB2 1PZ, UK;Toshiba Research Europe Ltd., Cambridge Research Laboratory, Cambridge CB4 0GZ, UK;Machine Intelligence Lab, Cambridge University Engineering Department, Cambridge CB2 1PZ, UK;Machine Intelligence Lab, Cambridge University Engineering Department, Cambridge CB2 1PZ, UK
Venue:
Speech Communication
Year:
2011

Citing 6
Cited 1

Restructuring speech representations using a pitch-adaptive time-frequency smoothing and an instantaneous-frequency-based F0 extraction: possible role of a repetitive structure in sounds

Speech Communication
Details of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005

IEICE - Transactions on Information and Systems
Decision tree state tying based on penalized Bayesian information criterion

ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis

IEICE - Transactions on Information and Systems
Review: Statistical parametric speech synthesis

Speech Communication
Probablistic modelling of F0 in unvoiced regions in HMM based speech synthesis

ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing

An intuitive style control technique in HMM-based expressive speech synthesis using subjective style intensity and multiple-regression global variance model

Speech Communication

Quantified Score

Hi-index	0.00

Visualization

Abstract

To achieve natural high quality synthesized speech in HMM-based speech synthesis, the effective modelling of complex acoustic and linguistic contexts is critical. Traditional approaches use context-dependent HMMs with decision tree based parameter clustering to model the full combinatorial of contexts. However, weak contexts, such as word-level emphasis in natural speech, are difficult to capture using this approach. Also, due to combinatorial explosion, incorporating new contexts within the traditional framework may easily lead to the problem of insufficient data coverage. To effectively model weak contexts and reduce the data sparsity problem, different types of contexts should be treated independently. Context adaptive training provides a structured framework for this whereby standard HMMs represent normal contexts and transforms represent the additional effects of weak contexts. In contrast to speaker adaptive training in speech recognition, separate decision trees have to be built for different types of context factors. This paper describes the general framework of context adaptive training and investigates three concrete forms: MLLR, CMLLR and CAT based systems. Experiments on a word-level emphasis synthesis task show that all context adaptive training approaches can outperform the standard full-context-dependent HMM approach. However, the MLLR based system achieved the best performance.