Time frequency mask-based single acoustic vector sensor (AVS) target voice enhancement method

Abstract

The invention relates to a time frequency mask-based single acoustic vector sensor (AVS) target voice enhancement method. According to the method, the arrival angle of the target voice is known, a method of combining a fixed beam former and a post-positioned Wiener filter is adopted for realizing target voice enhancement, and calculation of the weight value of the post-positioned Wiener filter involves self-power spectrum estimation of the target voice. Time frequency sparse characteristics of a voice signal are used, the time frequency point correlation arrival angle for receiving audio signals is estimated through calculating the ISDR (Inter-sensor data ratio) of component signals outputted by two gradient sensors in the AVS, time frequency mask is designed through calculating errors between the time frequency point correlation arrival angle and a target arrival angle, and thus self-power spectrum estimation of the target voice is acquired. According to the method of the invention, any noise prior knowledge does not needed, the target voice can be effectively enhanced in a complicated environment where multiple speakers exist, and interference voice can background noise can be suppressed. In addition, the operation complexity is low, the adopted microphone array size is small (about 1cm<3>), and application on a portable device is excessively facilitated.

Description

technical field [0001] The invention relates to a single acoustic vector sensor target voice enhancement method based on a time-frequency mask, and belongs to the technical field of voice signal processing. Background technique [0002] Speech enhancement is one of the core technologies in the field of speech processing. In the actual complex environment, when the microphone picks up the voice signal, it will inevitably be interfered by the noise of the surrounding environment, the noise of the transmission medium, the internal electrical noise of the communication equipment, the reverberation of the room, and the voice of other speakers, so the quality of the voice picked up is affected. influences. In order to reduce the impact of noise on speech and obtain high-quality speech, the requirements for speech enhancement technology are put forward. The traditional single-channel speech enhancement method is usually simple to implement and has obvious effects on incoherent no...

AI Technical Summary

Problems solved by technology

The traditional single-channel speech enhancement method is usually simple to implement and has obvious effects on incoherent noise, but it is difficult to enhance the target speech in noisy human voice environments (multiple speakers exist); the speech enhancement technology based on microphone arrays uses the signal Space-time spectrum information has a strong ability to suppress spatial interference and noise, and can obtain better performance than single-channel speech enhancement, but the speech enhancement performance increases with the increase in the number of microphones, so the volume of the microphone array is large, which limits Applications of this type of technology on small mobile devices

Images