Voice activity detection method, noise inhibition method and noise inhibition system

Abstract

The invention provides a voice activity detection method, which comprises the following steps of obtaining voice signals collected by a microphone and vibration signals collected by a sensor; converting the voice signals from a time domain to a frequency domain; converting the vibration signals from the time domain to the frequency domain; calculating the frequency domain correlation coefficient by using the voice signal and the vibration signals; calculating the detection quantity in the detection frequency range; when the detection quantity is higher than a preset threshold value, judging the voice signals collected by the microphone to be speaking voice of a wearer; otherwise, judging the voice signals collected by the microphone to have noise or interference signals. By calculating thefrequency domain correlation coefficient, the detection quantity is calculated in the detection frequency range, the voice activity detection accuracy is improved; the noise inhibition definition andthe intelligibility of the noise inhibition are improved.

Description

technical field [0001] The invention relates to the technical field of wireless communication, in particular to a voice activity detection method, a noise suppression method and a noise suppression system. Background technique [0002] With the development of society and the advancement of science and technology, earphones have gradually become a necessity in people's lives. When playing audio and talking on the phone, people often use earphones to achieve it. For wireless smart headphones with built-in voice assistants, it can help users check the weather, answer calls, broadcast the weather, monitor heart rate, etc. The intelligent music recommendation system based on deep learning will also be based on the user's listening habits, real-time heart rate, activity scenes, etc. , to provide accurate and diverse music recommendations, but wireless smart headphones with built-in voice assistants need to use Voice Activity Detection (VAD) to determine whether someone is speakin...

AI Technical Summary

Problems solved by technology

[0005] However, in the prior art, the accuracy of voice activity detection is improved by setting sensors to obtain vibration signals. It still uses the traditional algorithm to judge whether there is a wearer's call voice from the vibration signal, and the detection effect is not good. During the voice activity detection process There will still be detection errors in the

Images