Review: Statistical parametric speech synthesis
Speech Communication
Integrating articulatory features into HMM-based parametric speech synthesis
IEEE Transactions on Audio, Speech, and Language Processing
Robust speaker-adaptive HMM-based text-to-speech synthesis
IEEE Transactions on Audio, Speech, and Language Processing
Voice conversion using partial least squares regression
IEEE Transactions on Audio, Speech, and Language Processing
Voice conversion based on weighted frequency warping
IEEE Transactions on Audio, Speech, and Language Processing
IEEE Transactions on Audio, Speech, and Language Processing
Synthesis of child speech with HMM adaptation and voice conversion
IEEE Transactions on Audio, Speech, and Language Processing
Czech HMM-based speech synthesis: experiments with model adaptation
TSD'11 Proceedings of the 14th international conference on Text, speech and dialogue
Voice banking and voice reconstruction for MND patients
The proceedings of the 13th international ACM SIGACCESS conference on Computers and accessibility
Synthesis and perception of breathy, normal, and Lombard speech in the presence of noise
Computer Speech and Language
IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)
Hi-index | 0.00 |
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.