Cross-language emotional speech synthesis method and system

Abstract

The invention discloses a cross-language emotional speech synthesis method and system. The method comprises steps of establishing a context-dependent label format and a context-dependent clustering problem set; determining a first language annotation document, a second language annotation document, a target emotional Putonghua annotation document, an annotation document to be synthesized, a first language acoustic parameter, a second language acoustic parameter, a target emotional acoustic parameter; based on the first language annotation document, the second language annotation document, the target emotional Putonghua annotation document, the first language acoustic parameter, the second language acoustic parameter, and the target emotional acoustic parameter, determining the multi-speaker target emotional average acoustic model; and finally, inputting the annotation document to be synthesized into the multi-speaker target emotional average acoustic model to obtain a first language or / and a second language target emotional speech synthesis document to realize the synthesis of the same speaker or a different speaker cross-language emotional voice.

Description

technical field [0001] The invention relates to the technical field of multilingual emotional speech synthesis, in particular to a cross-language emotional speech synthesis method and system. Background technique [0002] The current speech synthesis technology has been able to synthesize more natural neutral speech, but when encountering human-computer interaction tasks such as robots and virtual assistants that need to imitate human behavior, simple neutral speech synthesis cannot meet people's needs . Emotional speech synthesis that can simulate human emotions and speaking styles has become the development trend of speech synthesis in the future. [0003] For the emotional speech synthesis of large languages ​​such as Chinese and English with a large number of users, the research investment is relatively high and the development level is relatively high; but for the emotional speech synthesis of small languages ​​such as Tibetan, Russian, and Spanish with a small number ...

AI Technical Summary

Problems solved by technology

Although the statistical parametric speech synthesis method has become the mainstream speech synthesis method, this method can only synthesize emotional speech in one language. If it is necessary to synthesize emotional speech in different languages, it is necessary to train multiple emotional speech synthesis systems. Speech synthesis systems need emotional voice training corpus of the language

Images