Name
Title | ||
|---|---|---|
Model Adaptation for HMM-Based Speech Synthesis under Minimum Generation Error Criterion |
Abstract | ||
|---|---|---|
In order to solve the issues related to the maximum likelihood (ML) based HMM training for HMM-based speech synthesis, a minimum generation error (MGE) criterion had been proposed. This paper continues to apply the MGE criterion to model adaptation for HMM-based speech synthesis. We introduce a MGE linear regression (MGELR) based model adaptation algorithm, where the transforms from source HMMs to target HMMs are optimized to minimize the generation errors for the adaptation data of the target speaker. The regression matrices for both mean vector and covariance matrix of Gaussian distribution are re-estimated. The proposed MGELR approach was compared with the maximum likelihood linear regression (MLLR) based model adaptation. Experimental results indicate that the generation errors were reduced after the MGELR-based model adaptation. And from the subjective listening test, the speaker similarity and the quality of the synthesized speech using MGELR were better than the results using MLLR. |
Year | DOI | Venue |
|---|---|---|
2008 | 10.1109/ISM.2008.36 | ISM |
Keywords | Field | DocType |
minimum generation error,minimum generation error criterion,linear regression,target speaker,speaker similarity,mge linear regression,generation error,regression analysis,maximum likelihood estimation,hmm training,model adaptation,covariance matrices,mge criterion,gaussian distribution,mge linear regression based model adaptation algorithm,regression matrices,speech synthesis,subjective listening test,hmm-based speech synthesis,synthesized speech,maximum likelihood,adaptation data,model adaptation algorithm,transforms,maximum likelihood linear regression based model adaptation,hidden markov models,error correction,vectors,covariance matrix,mgelr-based model adaptation,mean vector,speech,generalization error,training data | Speech synthesis,Regression,Pattern recognition,Regression analysis,Computer science,Speech recognition,Error detection and correction,Gaussian,Artificial intelligence,Covariance matrix,Hidden Markov model,Linear regression | Conference |
ISBN | Citations | PageRank |
978-0-7695-3454-1 | 0 | 0.34 |
References | Authors | |
6 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Long Qin | 1 | 27 | 3.93 |
| Yi-Jian Wu | 2 | 288 | 27.12 |
| Zhen-Hua Ling | 3 | 850 | 83.08 |
| Ren-Hua Wang | 4 | 344 | 41.36 |