Speech synthesis method and device

Abstract

The invention provides a speech synthesis method and device. The speech synthesis method comprises the steps that initial model parameters of alternative units are acquired in a pre-built model, an optimal unit sequence is determined according to the initial model parameters, and a cost value of the optimal unit sequence is calculated; if the cost value of the optimal unit sequence does not meet a preset condition, updated model parameters of the alternative units are acquired in the model, wherein the updated model parameters comprise model parameters of which the rhythm layers are one or multiple low-level component / components lower than those of the initial model parameters, and an optimal unit sequence is determined again according to the updated model parameters; speech units in the optimal unit sequence of which of the cost value meets the preset condition are determined as speech units to be spliced, so that the speech units to be spliced are conveniently spliced to obtain synthesized speech. According to the method, the accuracy of the selected speech units can be improved, and therefore the synthesized speech can be more natural and has the better expressive force.

Description

technical field [0001] The invention relates to the technical field of speech processing, in particular to a speech synthesis method and device. Background technique [0002] With the advent of the mobile era, people's demand for speech synthesis is increasing, such as novel reading, navigation voice, etc. And people are not only satisfied with the clarity and intelligibility of synthesized speech, but also require the synthesized speech to have better naturalness and expressiveness. The process of speech synthesis includes: preprocessing, word segmentation, part-of-speech tagging, phonetic notation, prosodic level prediction, acoustic parameter generation and speech generation, wherein, speech generation can be by using acoustic parameters to synthesize speech through a vocoder, or it can also be based on Acoustic parameters select the optimal unit from the corpus for splicing. For splicing synthesis, how to select the optimal unit sequence from the corpus will affect the...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, the path with the largest likelihood value in the candidate space is determined as the optimal unit sequence, but there will be deviations in this selection method, especially for sequences with a low average likelihood value, so that the synthesized speech is There are problems with naturalness and expressiveness

Images