Residual Compensation based on Articulatory Feature-based Phone Clustering for Hybrid Mandarin Speech Synthesis

Yi Chin Huang, Chung Hsien Wu, Shih Lun Lin

研究成果: Paper同行評審

2 引文 斯高帕斯(Scopus)

摘要

While speech synthesis based on Hidden Markov Models (HMMs) has been developed to successfully synthesize stable and intelligible speech with flexibility and small footprints in recent years, HMM-based method is still incapable to generate the speech with good quality and high naturalness. In this study, a hybrid method combining the unit-selection and HMMbased methods is proposed to compensate the residuals between the feature vectors of the natural phone units and the HMMsynthesized phone units to select better units and improve the naturalness of the synthesized speech. Articulatory features are adopted to cluster the phone units with similar articulation to construct the residual models of phone clusters. One residual model is characterized for each phone cluster using state-level linear regression. The candidate phone units of the natural corpus are selected by considering the compensated synthesized phone units of the same phone cluster, and then an optimal phone sequence is decided by the spectral features, contextual articulatory features, and pitch values to generate the synthesized speech with better naturalness. Objective and subjective evaluations were conducted and the comparison results to the HMM-based method and the conventional hybrid-based method confirm the improved performance of the proposed method.

原文English
頁面303-307
頁數5
出版狀態Published - 2013
事件8th ISCA Tutorial and Research Workshop on Speech Synthesis, SSW 2013 - Barcelona, Spain
持續時間: 2013 8月 312013 9月 2

Conference

Conference8th ISCA Tutorial and Research Workshop on Speech Synthesis, SSW 2013
國家/地區Spain
城市Barcelona
期間13-08-3113-09-02

All Science Journal Classification (ASJC) codes

  • 訊號處理
  • 軟體
  • 語言和語言學
  • 通訊

指紋

深入研究「Residual Compensation based on Articulatory Feature-based Phone Clustering for Hybrid Mandarin Speech Synthesis」主題。共同形成了獨特的指紋。

引用此