Title | ||
---|---|---|
Modulation Spectrum-Constrained Trajectory Training Algorithm For Hmm-Based Speech Synthesis |
Abstract | ||
---|---|---|
This paper presents a novel training algorithm for Hidden Markov Model (HMM)-based speech synthesis. One of the biggest issues causing significant quality degradation in synthetic speech is the over-smoothing effect often observed in generated speech parameter trajectories. Recently, we have found that a Modulation Spectrum (MS) of the generated speech parameters is sensitively correlated with the over-smoothing effect, and have proposed the parameter generation algorithm considering the MS. The over-smoothing effect is effectively alleviated by the proposed parameter generation algorithm. On the other hand, it loses the computationally-efficient generation processing of the conventional generation algorithm. In this paper, the MS is integrated into the training stage instead of the parameter generation stage in a similar manner as our previous work on Gaussian Mixture Model (GMM)-based spectral parameter trajectory conversion. The trajectory HMM is trained with a novel objective function consisting of both the conventional trajectory HMM likelihood and a newly implemented MS likelihood. This training framework is further extended to the F-0 component. The experimental results demonstrate that the proposed algorithm yields improvements in synthetic speech quality while preserving a capability of the computationally efficient generation processing. |
Year | Venue | Keywords |
---|---|---|
2015 | 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5 | HMM-based speech synthesis, over-smoothing, global variance, modulation spectrum, trajectory training |
Field | DocType | Citations |
Speech synthesis,Pattern recognition,Computer science,Speech recognition,Artificial intelligence,Hidden Markov model,Trajectory,Modulation spectrum | Conference | 1 |
PageRank | References | Authors |
0.36 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shinnosuke Takamichi | 1 | 75 | 22.08 |
Tomoki Toda | 2 | 1874 | 167.18 |
Alan W. Black | 3 | 4391 | 742.28 |
Satoshi Nakamura | 4 | 1099 | 194.59 |