A Unified Speech Enhancement System Based on Neural Beamforming With Parabolic Reflector

Abstract

This paper presents a unified speech enhancement system to remove both background noise and interfering speech in serious noise environments by jointly utilizing the parabolic reflector model and neural beamformer. First, the amplification property of paraboloid is discussed, which significantly improves the Signal-to-Noise Ratio (SNR) of a desired signal. Therefore, an appropriate paraboloid channel is analyzed and designed through the boundary element method. On the other hand, a time-frequency masking approach and a mask-based beamforming approach are discussed and incorporated in an enhancement system. It is worth noticing that signals provided by the paraboloid and the beamformer are exactly complementary. Finally, these signals are employed in a learning-based fusion framework to further improve the system performance in low SNR environments. Experiments demonstrate that our system is effective and robust in five different noisy conditions (speech interfered with factory, pink, destroyer engine, volvo, and babble noise), as well as in different noise levels. Compared with the original noisy speech, significant average objective metrics improvements are about Δ STOI = 0.28, Δ PESQ = 1.31, Δ fwSegSNR = 11.9.

Discrete Wavelet Transform and Spectral Subtraction Based Speech Enhancement Algorithm for Hearing Aid Application

“…Usually, a multichannel wiener lter [5], spectral subtraction [6], and Discrete Wavelet Transform [7] are used to estimate noise and perform speech enhancement in the use of hearing aids. In order to reduce the predicted noise, these algorithms are able to estimate the background noise power from the signal being processed.…”