Multi-speaker voice synthesis method based on variational auto-encoder

Abstract

The invention discloses a multi-speaker voice synthesis method based on a variational auto-encoder. The method comprises the following steps: extracting a phoneme-level duration parameter and a frame-level acoustic parameter of a to-be-synthesized speaker clean voice, inputting the normalized phoneme-level duration parameter into a first variational auto-encoder, and outputting a duration speakerlabel; inputting the normalized frame-level acoustic parameter into a second variational auto-encoder, and outputting an acoustic speaker label; extracting frame-level linguistic features and phoneme-level linguistic features from speech signals to be synthesized, wherein the speech signals include a plurality of speakers; inputting the duration speaker label and the normalized phoneme-level linguistic features into a duration prediction network, and outputting a current phoneme prediction duration; obtaining the frame-level linguistic characteristics of the phoneme through the current phonemeprediction duration, inputting the frame-level linguistic characteristics and the acoustic speaker label into an acoustic parameter prediction network, and outputting the normalized acoustic parameters of the prediction voice; and inputting the normalized predicted speech acoustic parameters into a vocoder, and outputting a synthesized speech signal.

Description

technical field [0001] The invention relates to a speech synthesis method, in particular to a multi-speaker speech synthesis method based on a variational autoencoder. Background technique [0002] Speech synthesis technology is an important technology for converting input text into speech, and it is also an important research content in the field of human-computer interaction. [0003] Traditional speech synthesis algorithms need to record a single-speaker sound library with a relatively comprehensive phoneme coverage to ensure that it can synthesize speech from various texts, but it will cause problems such as high recording costs, low efficiency, and only the speech of a single speaker. The multi-speaker speech synthesis supports parallel recording of speech by different speakers, and can synthesize speech from different speakers. Traditional multi-speaker speech synthesis often needs to obtain the speaker information of the current speech, and manually mark a speaker la...

AI Technical Summary

Problems solved by technology

[0003] The traditional speech synthesis algorithm needs to record a single-speaker sound library with a relatively comprehensive phoneme coverage to ensure that it can synthesize speech from various texts, but it will cause high recording costs, low efficiency, and the problem of only synthesizing the speech of a single speaker

Images