Speech synthesis method and device based on rhythm feature prediction, terminal and medium

Abstract

The invention discloses a speech synthesis method based on rhythm feature prediction. The speech synthesis method comprises the steps of obtaining a to-be-synthesized text; inputting the to-be-synthesized text into a preset rhythm prediction model, obtaining rhythm features of the to-be-synthesized text as first rhythm features, and determining target rhythm features according to the first rhythmfeatures, the rhythm features of the to-be-synthesized text including rhythm word features, rhythm phrase features and rhythm intonation phrase features; and performing voice synthesis according to the target rhythm feature to generate a target voice corresponding to the to-be-synthesized text. In addition, the invention also discloses a speech synthesis device based on rhythm feature prediction,an intelligent terminal and a computer readable storage medium. By adopting the method and the device, the accuracy of text rhythm feature prediction can be improved, and the speech synthesis effect is improved.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular to a speech synthesis method, device, intelligent terminal and computer-readable storage medium based on prosodic feature prediction. Background technique [0002] With the rapid development of mobile Internet and artificial intelligence technology, there are more and more voice synthesis scenarios such as voice broadcast, listening to novels, listening to news, and intelligent interaction. Speech synthesis can convert text, text, etc. into natural speech output. [0003] In the process of speech synthesis, it is necessary to predict the prosody of the text. Prosody affects the naturalness and fluency of pronunciation. A good prosody prediction result will make the synthesized speech more similar to the pauses of human speech, thus making the synthesized speech more natural. [0004] However, in the existing prosody prediction schemes, the training an...

AI Technical Summary

Problems solved by technology

However, there is a certain error between the prosodic feature prediction result obtained through the above scheme and the real prosodic feature, which leads to insufficient accuracy of prosody prediction, resulting in insufficient effect of speech synthesis

[0005] That is to say, in the above speech synthesis scheme, the effect of the synthesized speech is insufficient due to the insufficient accuracy of prosody prediction

Images