Voice signal processing method and device, storage medium and terminal equipment

Abstract

The invention discloses a voice signal processing method and device, a storage medium and terminal equipment. The method comprises the steps:obtaining N voice features in a voice segment; performing preset irreversible transformation processing on the N voice features to obtain N first voice features; dividing the N first voice features into K voice feature blocks, the voice feature block comprising a plurality of first voice features, N being larger than or equal to K larger than 0; adjusting the first voice feature in each voice feature block to obtain N second voice features, the adjustmentprocessing being to intercept part of the first voice features from the kth voice feature block, or fill new voice features according to the first voice features in the kth voice feature block, K being larger than or equal to k larger than 0; inputting the N second voice features into a preset vocoder, and synthesizing a voice signal after voice changing; according to the invention, the identityof the user is difficult to identify from the voice signal after voice changing, and the privacy protection of the user is enhanced.

Description

technical field [0001] The present invention relates to the field of speech technology, in particular to a speech signal processing method, device, storage medium and terminal equipment. Background technique [0002] With the rapid development of speech signal processing technology and the popular promotion of social platforms, voice change has become an important research direction in the field of speech signal processing. It can be applied in many fields such as secure communication, entertainment communication, etc., and has a good prospect. [0003] In the prior art, the following four methods are used to change the voice. The first one is to change the voice by changing the pitch. By changing the frequency of the sound source, the higher the frequency, the higher the pitch, and the lower the frequency, the higher the pitch. It is also possible to increase or decrease the pitch of the music played by changing the playback frequency, such as accelerating or slowing down t...

AI Technical Summary

Problems solved by technology

For modifying the frequency of formants, most methods are based on parameter synthesis algorithms. The common problems of these methods are that the amount of calculation is relatively large, manual intervention is required, and the naturalness of the synthesized speech is relatively poor.

[0006] The fourth is to change the voice by adjusting the EQ equalizer. When listening to music files in MP3 format, the EQ equalizer is often used to adjust the sound effect of the digital sound. It is divided into multiple frequency bands, and the signals of different frequencies in the multiple frequency bands are adjusted and gained separately. It can only pray to compensate for the defects of speakers and sound fields, compensate and modify various sound sources and other auxiliary functions, but similar to chipmunks, Ventriloquism, ghost voice and other special sound effects cannot be achieved by adjusting the EQ equalizer.

[0007] However, the above four methods all change the voice from the perspective of the voice frequency. The voice is changed by raising the treble or lowering the bass, which is easy to be reversed, thus revealing the identity of the speaker, and cannot achieve the effect of privacy protection.

Images