Speech synthesis method and apparatus, and readable storage medium

Abstract

A speech synthesis method includes: converting a text input sequence into a text feature representation sequence; inputting the text feature representation sequence into an encoder including N encoding layers; the N encoding layers including an encoding layer Eand an encoding layer E; the encoding layer Eincluding a first multi-head self-attention network; acquiring a first attention matrix and a historical text encoded sequence outputted by the encoding layer E, and generating a second attention matrix of the encoding layer Eaccording to residual connection between the first attention matrix and the first multi-head self-attention network and the historical text encoded sequence; and generating a target text encoded sequence of the encoding layer Eaccording to the second attention matrix and the historical text encoded sequence, and generating synthesized speech data matched with the text input sequence based on the target text encoded sequence.