Dual Microphone Voice Activity Detection Based on Reliable Spatial Cues

Abstract

Two main spatial cues that can be exploited for dual microphone voice activity detection (VAD) are the interchannel time difference (ITD) and the interchannel level difference (ILD). While both ITD and ILD provide information on the location of audio sources, they may be impaired in different manners by background noises and reverberation and therefore can have complementary information. Conventional approaches utilize the statistics from all frequencies with fixed weight, although the information from some time–frequency bins may degrade the performance of VAD. In this letter, we propose a dual microphone VAD scheme based on the spatial cues in reliable frequency bins only, considering the sparsity of the speech signal in the time–frequency domain. The reliability of each time–frequency bin is determined by three conditions on signal energy, ILD, and ITD. ITD-based and ILD-based VADs and statistics are evaluated using the information from selected frequency bins and then combined to produce the final VAD results. Experimental results show that the proposed frequency selective approach enhances the performances of VAD in realistic environments.

Biosignal Sensors and Deep Learning-Based Speech Recognition: A Review

“…A major flaw in the language-based interface is that it is very sensitive to ambient noise, making it difficult to differentiate and classify signal to noise. To address this, a microphone voice activity detection (VAD) scheme [ 55 ] that enhances performance in a variety of noise environments in consideration of the sparsity of the speech signal in the time-frequency domain is proposed. And the language-based interface with the robot’s control is developed [ 56 ] and it reduced the ambient noise by 30%, the resulting inaccuracy has been improved.…”

Multi-TALK: Multi-Microphone Cross-Tower Network for Jointly Suppressing Acoustic Echo and Background Noise

“…Spatial cues between multi-channel signals such as inter-channel time difference (or inter-channel phase difference) and inter-channel level difference can indicate the location of the speech source. These spatial characteristics have been shown to be particularly beneficial when combined with spectral characteristics over the frequency domain in several fields, such as source separation, speech enhancement, and voice activity detection [ 16 , 17 , 18 , 19 , 20 , 21 , 22 , 23 ]. Unfortunately, these spatial features are typically extracted in the frequency domain using STFT, making it difficult to integrate perfectly using the time domain method.…”