Song synthesis method, device and equipment and storage medium

Abstract

The invention relates to artificial intelligence, and discloses a song synthesis method which comprises the steps: obtaining lyric recitation audio and music score information; performing duration labeling on the lyric recitation audio through a preset voice recognition model and a lyric pinyin text to obtain recitation duration; analyzing initial acoustic parameters from the lyric recitation audio through a preset vocoder; extracting singing duration from the lyric pinyin text according to a preset initial consonant variable speed dictionary, the rhythm information and the beat information; performing speed change processing on the initial acoustic parameters according to a preset speed change algorithm, the recitation duration and the singing duration; performing formant enhancement processing on the frequency spectrum envelope after speed change to obtain an enhanced frequency spectrum envelope; performing correction processing based on the pitch information, the singing duration and the fundamental frequency after speed change to obtain a corrected fundamental frequency; and performing song synthesis processing on the processed acoustic parameters through the preset vocoder. The invention also relates to a blockchain, and the synthesized song is stored in the blockchain.

Description

technical field [0001] The invention relates to the field of voice signal processing, in particular to a song synthesis method, device, equipment and storage medium. Background technique [0002] In recent decades, singing synthesis technology has gradually attracted the attention of the industry. Inspired by speech synthesis technology, singing synthesis technology based on waveform splicing and parameter synthesis has gradually emerged, but most of the related technical research focuses on the direction of text synthesis singing or lyrics synthesis singing, that is, converting text information into singing audio, while It is not directly converting speech audio to singing audio. [0003] Some people in the industry have also developed an algorithm that automatically distinguishes between speaking and singing, but they have not further applied this technology to the direction of reciting synthetic singing. Reciting synthetic singing is to directly assign the voice of natur...

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to solve the technical problems of waveform breakage and unnatural transition in the traditional variable-speed and pitch-shifting algorithm based on the superposition operation at the waveform level

Images