Voice processing method, mobile terminal and computer readable storage medium

Abstract

The invention provides a voice processing method. The method comprises the steps that a subject voice signal and an object voice signal are collected through a microphone; when a mobile terminal is ina first working mode, a sound track model of the subject voice signal is analyzed to extract sound track model parameters of the subject voice signal; when the mobile terminal is in a second workingmode, a fundamental tone of the object voice signal is analyzed to extract fundamental tone characteristics of the object voice signal; and the object voice signal is processed based on the sound track model parameters and the fundamental tone characteristics to obtain a target voice signal. The invention further provides the mobile terminal and a computer readable storage medium. Through the method, the object voice signal can be processed based on the extracted sound track model parameters of the subject voice signal and the extracted fundamental tone characteristics of the object voice signal, so that the target voice signal which conforms to the sound track model of the subject voice signal and has invariable fundamental tone characteristics of the object voice signal is obtained, anduser experience is improved.

Description

technical field [0001] The present application relates to the technical field of speech processing, and in particular to a speech processing method, a mobile terminal and a computer-readable storage medium. Background technique [0002] Generally, speech signals have certain characteristics, and users can identify speakers through these characteristics. Due to the difference in people's hearing levels, the speech signal of the same speech rate may feel that the speech speed is too fast for some people so that they cannot hear clearly, and for another part of the people may feel that the speech speed is so slow that they feel that it is a waste of time. Therefore, the mobile terminal needs to appropriately change the intonation and speech rate of the received voice signal according to people's actual needs. [0003] However, generally changing the speech speed by speeding up or slowing down the playback speed will cause the playback speed to be unsuitable for the user's spee...

AI Technical Summary

Problems solved by technology

[0003] However, usually by speeding up or slowing down the playback speed to change the speech rate, the playback speed will not be suitable for the user's speech rate habit, which affects the user's experience

At the same time, because the change of speech rate will lead to the change of intonation, the user cannot distinguish the speaker according to the changed voice signal, which seriously affects the user's experience.

Images