Voice activity detection method, related device and equipment

Abstract

The invention discloses a voice activity detection method, comprising: receiving voice data; the voice data includes multiple frames of voice signals; calculating the energy and spectral entropy of one frame of voice signals; The root of the spectral entropy; and according to the energy after the root or the spectral entropy after the root, the spectral entropy energy root of the speech signal is calculated; when the spectral entropy energy root of the speech signal is less than the first preset threshold, It is judged that the voice signal is a non-voice frame; or when the spectral entropy energy root of the voice signal is not less than the first preset threshold, it is judged that the voice signal is a voice frame. The invention also discloses a voice activity detection device and a voice activity. The detection device solves the problem that the threshold setting of the solution based on short-term energy and spectral entropy in the prior art is greatly affected by the recording environment, or the solution based on the energy product of spectral entropy cannot effectively reflect the characteristics of the speech frame, resulting in the inability to accurately detect the speech segment. technical problem.

Description

technical field [0001] The invention relates to the field of computers, in particular to a voice activity detection method, a voice activity detection device and a voice activity detection device. Background technique [0002] Speech recognition is an interdisciplinary subject. In the past two decades, speech recognition technology has made significant progress and has begun to move from the laboratory to the market. With the development of speech recognition technology, speech recognition technology will enter various fields such as industry, home appliances, communications, automotive electronics, medical care, home services, and consumer electronic products. [0003] Voice Activity Detection (VAD), also known as voice activity detection, voice endpoint detection, voice boundary detection, etc., is a technology used for voice processing to detect the presence of voice signals. VAD is standard for speech recognition technology. [0004] In the prior art, the VAD algorith...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the embodiments of the present invention is to provide a method for detecting voice activity, a device for detecting voice activity, a device for detecting voice activity, and a computer-readable storage medium, so as to solve the problems in the prior art based on short-term energy and The threshold setting of the spectral entropy scheme is greatly affected by the recording environment, or the scheme based on the spectral entropy energy product cannot effectively reflect the characteristics of the speech frame, resulting in the technical problem that the speech segment cannot be accurately detected

Images