Prosody Modification on Mixed-language Speech Synthesis

Abstract

This paper proposes a method to generate natural prosody parameters in Chinese and English mixed-language speech synthesis system which is based on separate Chinese, English, and a small bilingual corpus. Prosodic assimilation of English words to Chinese contexts can be found by observing the bilingual corpus. The most obvious assimilation characteristics are the wider pitch range and the longer duration. A prosody modification model based on this observation is proposed to modify mono-lingual prosody parameters to adapt for mixed-lingual environment. Experiments have proved that more natural mixed-lingual prosody can be generated with our model.