Voice activity detection method and device, and readable storage medium

Abstract

The invention discloses a voice activity detection method and device, and a readable storage medium. The voice activity detection method comprises the steps: obtaining a collected voice signal; respectively adopting a voice noise reduction algorithm and a harmonic detection algorithm to judge whether the voice signal has voice activity or not; and when both the voice noise reduction algorithm andthe harmonic detection algorithm judge that the voice signal has voice activity, judging that the voice activity is detected from the voice signal. By adopting the scheme, the voice activity can be accurately detected.

Description

technical field [0001] The invention belongs to the technical field of voice, and in particular relates to a voice activity detection method and device, and a readable storage medium. Background technique [0002] Traditional voice activity detection methods, such as detection methods based on volume or microphone level, often have false detections in noisy environments, which can lead to false activation of voice devices, which not only consumes electricity, but also disturbs others. [0003] Most of the existing voice activity detection methods are based on the judgment of sound energy, which mainly has the following two shortcomings: one is that the voice cannot be accurately distinguished in a noisy environment, such as in noisy public places and outdoor wind noise, etc.; the other is that in a quiet environment Under normal circumstances, it is easy to cause false detection due to some sudden non-speech sounds, such as the ringing of the phone, the sound of closing the ...

AI Technical Summary

Problems solved by technology

[0002] Traditional voice activity detection methods, such as detection methods based on volume or microphone level, often have false detections in noisy environments, resulting in false activation of voice devices, which not only consumes electricity, but also disturbs others

[0003] Most of the existing voice activity detection methods are based on the judgment of sound energy, which mainly has the following two shortcomings: one is that the voice cannot be accurately distinguished in a noisy environment, such as in noisy public places and outdoor wind noise, etc.; the other is that in a quiet environment In this situation, it is easy to cause false detection due to some sudden non-speech sounds, such as telephone ringing, door closing, etc.

Images