Personalising speech-to-speech translation: Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis
Computer Speech & Language(2013)
摘要
In this paper we present results of unsupervised cross-lingual speaker adaptation applied to text-to-speech synthesis. The application of our research is the personalisation of speech-to-speech translation in which we employ a HMM statistical framework for both speech recognition and synthesis. This framework provides a logical mechanism to adapt synthesised speech output to the voice of the user by way of speech recognition. In this work we present results of several different unsupervised and cross-lingual adaptation approaches as well as an end-to-end speaker adaptive speech-to-speech translation system. Our experiments show that we can successfully apply speaker adaptation in both unsupervised and cross-lingual scenarios and our proposed algorithms seem to generalise well for several language pairs. We also discuss important future directions including the need for better evaluation metrics.
更多查看译文
关键词
hmm-based speech synthesis,speech recognition,unsupervised cross-lingual speaker adaptation,present result,hmm statistical framework,synthesised speech output,cross-lingual scenario,cross-lingual adaptation,speech-to-speech translation,speaker adaptation,end-to-end speaker adaptive speech-to-speech,speech synthesis,machine translation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要