Speech synthesis method and device, equipment and storage medium

Abstract

The invention discloses a speech synthesis method and device, equipment and a storage medium. In the process of performing speech synthesis on a to-be-synthesized original text, auxiliary synthesis features corresponding to a matching text of a text fragment matched with the original text are referred; the auxiliary synthesis features are features which are determined based on a pronunciation audio corresponding to the matching text and are used for assisting speech synthesis; by referring to the auxiliary synthesis features corresponding to the matching text, the pronunciation information in the pronunciation audio corresponding to the matching text can be used for assisting speech synthesis of the original text, so that the reference information during the speech synthesis of the original text is enriched, and the speech synthesis quality of the original text is improved. The speech synthesis method of the invention can be suitable for speech synthesis systems with front-end preprocessing and speech synthesis systems without front-end preprocessing; the auxiliary synthesis features can be used as front-end text analysis results and can also directly assist the speech synthesis systems in speech synthesis, and can improve the quality of synthesized speech.

Description

technical field [0001] The present application relates to the technical field of speech processing, and more specifically, relates to a speech synthesis method, device, equipment and storage medium. Background technique [0002] In recent years, with the development of information and the rise of artificial intelligence, human-computer interaction has become more and more important. Among them, speech synthesis is a hot spot in human-computer interaction research at home and abroad. Speech synthesis is the process of synthesizing the input original text to be synthesized into speech output. [0003] The traditional speech synthesis model is generally based on the end-to-end speech synthesis scheme, that is, the training text and the corresponding speech data or waveform data are directly used to train the speech synthesis model, and the trained speech synthesis model is based on the input original text to be synthesized. That is, synthesized speech or waveform data can be ...

AI Technical Summary

Problems solved by technology

[0004] Existing speech synthesis schemes only refer to the original text for speech synthesis, resulting in error-prone synthetic speech and poor synthesis effect

Images