Multiple-average-voice-based speech synthesis
Acoustics, Speech and Signal Processing(2014)
摘要
This paper describes a novel approach for the speaker adaptation of statistical parametric speech synthesis systems based on the interpolation of a set of average voice models (AVM). Recent results have shown that the quality/naturalness of adapted voices depends on the distance from the average voice model used for speaker adaptation. This suggests the use of several AVMs trained on carefully chosen speaker clusters from which a more suitable AVM can be selected/interpolated during the adaptation. In the proposed approach a set of AVMs, a multiple-AVM, is trained on distinct clusters of speakers which are iteratively re-assigned during the estimation process initialised according to metadata. During adaptation, each AVM from the multiple-AVM is first adapted towards the target speaker. The adapted means from the AVMs are then interpolated to yield the final speaker adapted mean for synthesis. It is shown, performing speaker adaptation on a corpus of British speakers with various regional accents, that the quality/naturalness of synthetic speech of adapted voices is significantly higher than when considering a single factor-independent AVM selected according to the target speaker characteristics.
更多查看译文
关键词
interpolation,speech synthesis,AVM,British speakers,adapted voices,average voice model,estimation process,final speaker,interpolation,metadata,multiple average voice based speech synthesis,speaker adaptation,speaker clusters,statistical parametric speech synthesis systems,synthetic speech,target speaker,target speaker characteristics,HMM-Based speech synthesis,cluster adaptive training,multiple average voice model,speaker adaptation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络