Abstract
The use of multiple spatially distributed microphones allows performing spatial filtering along with conventional temporal filtering, which can better reject the interference signals, leading to an overall improvement of the speech quality. In this paper, we propose a novel dual-microphone generalized sidelobe canceller (GSC) algorithm assisted by a bone-conduction (BC) sensor for speech enhancement, which is named BC-assisted GSC (BCA-GSC) algorithm. The BC sensor is relatively insensitive to the ambient noise compared to the conventional air-conduction (AC) microphone. Hence, BC speech can be analyzed to generate very accurate voice activity detection (VAD), even in a high noise environment. The proposed algorithm incorporates the VAD information obtained by the BC speech into the adaptive blocking matrix (ABM) and adaptive noise canceller (ANC) in GSC. By using VAD to control ABM and combining VAD with signal-to-interference ratio (SIR) to control ANC, the proposed method could suppress interferences and improve the overall performance of GSC significantly. It is verified by experiments that the proposed GSC system not only improves speech quality remarkably but also boosts speech intelligibility.
Highlights
Speech technology plays an important role in speech communication and humancomputer interaction
The generalized sidelobe canceller (GSC) is an effective technique for an adaptive microphone array, which is commonly used in speech enhancement applications
Khayer et al proposed replacing the blocking matrix in GSC with a linear constrained minimum variance (LCMV) beamformer to alleviate the leakage of the desired signal and effectively reduce the noise [9]
Summary
Speech technology plays an important role in speech communication and humancomputer interaction. Khayer et al proposed replacing the blocking matrix in GSC with a linear constrained minimum variance (LCMV) beamformer to alleviate the leakage of the desired signal and effectively reduce the noise [9]. Despite the effectiveness of the various proposed methods, the accurate control of the ABM and ANC, especially under highly non-stationary noise and low signal-to-noise ratio (SNR) conditions, is still very challenging. It can be observed the BC speech signal is much less deteriorated by the ambient acoustic noise, but its high frequency spectrum (>800 Hz) is seriously attenuated due to the low-pass nature of the human body.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
