Analysis of Speaker Adaptation Algorithms for HMM-Based Speech Synthesis and a Constrained SMAPLR Adaptation Algorithm
Top Cited Papers
- 6 January 2009
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech, and Language Processing
- Vol. 17 (1), 66-83
- https://doi.org/10.1109/tasl.2008.2006647
Abstract
In this paper, we analyze the effects of several factors and configuration choices encountered during training and model construction when we want to obtain better and more stable adaptation in HMM-based speech synthesis. We then propose a new adaptation algorithm called constrained structural maximum a posteriori linear regression (CSMAPLR) whose derivation is based on the knowledge obtained in this analysis and on the results of comparing several conventional adaptation algorithms. Here, we investigate six major aspects of the speaker adaptation: initial models; the amount of the training data for the initial models; the transform functions, estimation criteria, and sensitivity of several linear regression adaptation algorithms; and combination algorithms. Analyzing the effect of the initial model, we compare speaker-dependent models, gender-independent models, and the simultaneous use of the gender-dependent models to single use of the gender-dependent models. Analyzing the effect of the transform functions, we compare the transform function for only mean vectors with that for mean vectors and covariance matrices. Analyzing the effect of the estimation criteria, we compare the ML criterion with a robust estimation criterion called structural MAP. We evaluate the sensitivity of several thresholds for the piecewise linear regression algorithms and take up methods combining MAP adaptation with the linear regression algorithms. We incorporate these adaptation algorithms into our speech synthesis system and present several subjective and objective evaluation results showing the utility and effectiveness of these algorithms in speaker adaptation for HMM-based speech synthesis.Keywords
This publication has 41 references indexed in Scilit:
- New approach to the polyglot speech generation by means of an HMM-based speaker adaptable synthesizerSpeech Communication, 2006
- HMM-Based Emotional Speech Synthesis Using Average Emotion ModelLecture Notes in Computer Science, 2006
- A compact model for speaker-adaptive trainingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A structural Bayes approach to speaker adaptationIEEE Transactions on Speech and Audio Processing, 2001
- Maximum likelihood linear transformations for HMM-based speech recognitionComputer Speech & Language, 1998
- Speaker adaptation using constrained estimation of Gaussian mixturesIEEE Transactions on Speech and Audio Processing, 1995
- Elliptically Contoured Models in StatisticsPublished by Springer Science and Business Media LLC ,1993
- An adaptive algorithm for mel-cepstral analysis of speechPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- Continuously variable duration hidden Markov models for automatic speech recognitionComputer Speech & Language, 1986
- Explicit modelling of state occupancy in hidden Markov models for automatic speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1985