Dual-Mic Speech Enhancement Based on TF-GSC with Leakage Suppression and Signal Recovery

The transfer function-generalized sidelobe canceller (TF-GSC) is one of the most popular structures for the adaptive beamformer used in multi-channel speech enhancement. Although the TF-GSC has shown decent performance, a certain amount of steering error is inevitable, which causes leakage of speech components through the blocking matrix (BM) and distortion in the fixed beamformer (FBF) output. In this paper, we propose to suppress the leaked signal in the output of the BM and restore the desired signal in the FBF output of the TF-GSC. To reduce the risk of attenuating speech in the adaptive noise canceller (ANC), the speech component in the output of the BM is suppressed by applying a gain function similar to the square-root Wiener filter, assuming that a certain portion of the desired speech should be leaked into the BM output. Additionally, we propose to restore the attenuated desired signal in the FBF output by adding some of the microphone signal components back, depending on how microphone signals are related to the FBF and BM outputs. The experimental results showed that the proposed TF-GSC outperformed conventional TF-GSC in terms of the perceptual evaluation of speech quality (PESQ) scores under various noise conditions and the direction of arrivals for the desired and interfering sources.

A Robust Dual-Microphone Generalized Sidelobe Canceller Using a Bone-Conduction Sensor for Speech Enhancement

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.

A Real-Time Dual-Microphone Speech Enhancement Algorithm Assisted by Bone Conduction Sensor

The quality and intelligibility of the speech are usually impaired by the interference of background noise when using internet voice calls. To solve this problem in the context of wearable smart devices, this paper introduces a dual-microphone, bone-conduction (BC) sensor assisted beamformer and a simple recurrent unit (SRU)-based neural network postfilter for real-time speech enhancement. Assisted by the BC sensor, which is insensitive to the environmental noise compared to the regular air-conduction (AC) microphone, the accurate voice activity detection (VAD) can be obtained from the BC signal and incorporated into the adaptive noise canceller (ANC) and adaptive block matrix (ABM). The SRU-based postfilter consists of a recurrent neural network with a small number of parameters, which improves the computational efficiency. The sub-band signal processing is designed to compress the input features of the neural network, and the scale-invariant signal-to-distortion ratio (SI-SDR) is developed as the loss function to minimize the distortion of the desired speech signal. Experimental results demonstrate that the proposed real-time speech enhancement system provides significant speech sound quality and intelligibility improvements for all noise types and levels when compared with the AC-only beamformer with a postfiltering algorithm.

A COMPARISON ON VARIANTS OF LMS USED IN FIR ADAPTIVE NOISE CANCELLERS FOR FETAL ECG EXTRACTION

Fetal electrocardiogram (FECG) non-invasively obtained through abdominal recordings serves as a promising diagnostic tool for fetal health monitoring during pregnancy. However, in the abdominal ECG (AECG) signal, FECG overlaps with maternal ECG (MECG) in both temporal and spectral domains in addition to interference from various sources like electromyogram, electrogastrogram, motion artifacts and other noises. The objective of this paper is to eliminate MECG components from AECG signal to extract FECG signal through FIR adaptive noise canceller (ANC) with filter coefficients updated using adaptive algorithms. Adaptive filters are suitable for current problem of interest and Least Mean Square (LMS) and its variants are analyzed for the problem of FECG extraction. We have compared the four variants of LMS such as normalized LMS (NLMS), sign-error algorithm, least mean fourth (LMF) algorithms for FECG extraction. The algorithms are evaluated using real-time abdominal ECG recordings acquired from daisy database. The performance of each algorithm is evaluated using various parameters like sensitivity, accuracy, positive predictive values and [Formula: see text] score. Further, the convergence rate for different algorithms are plotted and analyzed. From the simulation results, it is observed that the LMF algorithm outperforms its counterparts by providing an accuracy and positive predictive value of 73.3%, sensitivity of 100% and [Formula: see text] measure of 84.5%. The convergence plots obtained justify that LMF algorithm has a faster convergence rate compared to the other variants of LMS.

A Hybrid Optimization Method OWGWA for EEG/ERP Adaptive Noise Canceller With Controlled Search Space

In this paper, a system for filtering event-related potentials/electroencephalograph is exhibited by adaptive noise canceller through an optimization algorithm, oppositional hybrid whale-grey wolf optimization algorithm (OWGWA). The OWGWA can choose the control parameters of the grey wolf algorithm utilizing whale parameters. To balance out the randomness of optimization strategies another methodology is implemented called controlled search space. Adaptive filter's noise reduction capability has been tested through adding adaptive white Gaussian noise over contaminated EEG signals at different noise levels. The performance of the proposed OWGWA-CSS algorithm is evaluated by signal to noise ratio in dB, mean value, and the relationship between resultant and input ERP. In this work, ANCs are also implemented by utilizing other optimization techniques. In average cases of noisy environment, comparative analysis shows that the proposed OWGWA-CSS technique provides higher SNR value, significantly lower mean and higher correlation as compared to other techniques.

Adaptive Noise Cancellation System Using a Recursive Least Squares Filter

In this paper, we show an Adaptive Noise Canceller (ANC) that estimate an original audio a signal measured with noise. Adaptive system is implemented using a Recursive Least Squares filter (RLS). Its design parameters consider the filter order, forgetting factor and initial conditions to obtain optimal coefficients through iterations. A medium square error (MSE) around to 10-6 is reached, and with this it makes possible a low-cost implementation.