Speech Separation Algorithm Using Gated Recurrent Network Based on Microphone Array

Speech separation is an active research topic that plays an important role in numerous applications,such as speaker recognition,hearing pros-thesis,and autonomous robots.Many algorithms have been put forward to improve separation performance.However,speech separation in reverberant noisy environment is still a challenging task.To address this,a novel speech separation algorithm using gate recurrent unit(GRU)network based on microphone array has been proposed in this paper.The main aim of the proposed algorithm is to improve the separation performance and reduce the computational cost.The proposed algorithm extracts the sub-band steered response power-phase transform(SRP-PHAT)weighted by gammatone filter as the speech separation feature due to its discriminative and robust spatial position in formation.Since the GRU net work has the advantage of processing time series data with faster training speed and fewer training parameters,the GRU model is adopted to process the separation featuresof several sequential frames in the same sub-band to estimate the ideal Ratio Masking(IRM).The proposed algorithm decomposes the mixture signals into time-frequency(TF)units using gammatone filter bank in the frequency domain,and the target speech is reconstructed in the frequency domain by masking the mixture signal according to the estimated IRM.The operations of decomposing the mixture signal and reconstructing the target signal are completed in the frequency domain which can reduce the total computational cost.Experimental results demonstrate that the proposed algorithm realizes omnidirectional speech sep-aration in noisy and reverberant environments,provides good performance in terms of speech quality and intelligibility,and has the generalization capacity to reverberate.

STUDY ON FLAP SIDE-EDGE NOISE BASED ON THE FLY-OVER MEASUREMENTS WITH A PLANAR MICROPHONE ARRAY

A large planar microphone array, which consists of 111 microphones, was successfully applied to measure a two dimensional mapping of the sound sources on landing aircraft. The focus was on the flap side edge noise source in this paper. The spectra, directivity and sound pressure level of flap side edge noise of 10 aircraft were presented in this paper. It is found that the spectrum of flap side edge noise is a broadband noise with some tones in some cases. Two different types of tone sources are found. It is proposed that one type of these tone sources is trailing edge semi baffled dipole source, and another is produced from the shedding of vortex from the wing cusp. The total sound pressure level of flap side edge broadband noise has no obvious directionality. However, the directivity of the tone noise in the flap side edge noise spectrum is obvious. It is demonstrated that the local flow field is the key to controlling the flap side edge noise.

A FAST SEARCH METHOD OF STEERED RESPONSE POWER WITH SMALL-APERTURE MICROPHONE ARRAY FOR SOUND SOURCE LOCALIZATION

The Steered Response Power(SRP)method works well for sound source localization in noisy and reverberant environment.However,the large computation complexity limits its practical application.In this paper,a fast SRP search method is proposed to reduce the computational complexity using small-aperture microphone array.The proposed method inspired by the SRP spatial spectrum includes two steps:first,the proposed method estimates the azimuth of the sound source roughly and determines whether the sound source is in far field or near field;then,different fine searching operations are performed according to the sound source being in far field or near field.Experiments both in simulation environments and real environments have been performed to compare the localization accuracy and computation complexity of the proposed method with those of the conventional SRP-PHAT algorithm.The results show that,the proposed method has a comparative accuracy with the conventional SRP algorithm,and achieves a reduction of 93.62%in computation complexity compared to the conventional SRP algorithm.

Noise Source Identification Applied in Electric Power Industry Using Microphone Arrays

The noise source identification is an important issue in noise reduction and condition monitoring(CM) for machines in- site using microphone arrays. In this paper, we propose a new approach to optimize array configuration based on particles swarm optimization algorithm in order to improve noise source identification and condition monitoring performance. Two distinct optimized array configurations are designed under the certain conditions. Furthermore, an acoustic imaging equipment is developed to carry out experiments on transformer substation equipment and wind turbine generator, which demonstrate that the acoustic imaging system allows a high resolution in identifying main noise sources for noise reduction and abnormal noise sources for condition monitoring.

Microphone Array-Based Sound Source Localization Using Convolutional Residual Network

Microphone array-based sound source localization(SSL)is widely used in a variety of occasions such as video conferencing,robotic hearing,speech enhancement,speech recognition and so on.The traditional SSL methods cannot achieve satisfactory performance in adverse noisy and reverberant environments.In order to improve localization performance,a novel SSL algorithm using convolutional residual network(CRN)is proposed in this paper.The spatial features including time difference of arrivals(TDOAs)between microphone pairs and steered response power-phase transform(SRPPHAT)spatial spectrum are extracted in each Gammatone sub-band.The spatial features of different sub-bands with a frame are combine into a feature matrix as the input of CRN.The proposed algorithm employ CRN to fuse the spatial features.Since the CRN introduces the residual structure on the basis of the convolutional network,it reduce the difficulty of training procedure and accelerate the convergence of the model.A CRN model is learned from the training data in various reverberation and noise environments to establish the mapping regularity between the input feature and the sound azimuth.Through simulation verification,compared with the methods using traditional deep neural network,the proposed algorithm can achieve a better localization performance in SSL task,and provide better generalization capacity to untrained noise and reverberation.

A New Calibration Method for Microphone Array with Gain, Phase, and Position Errors

Microphone array can be used in sound source localization and separation. But gain, phase, and position errors can seriously influence the performance of localization algorithms such as multiple signal classification （MUSIC） algorithm. In this paper, a new calibration method for microphone array with gain, phase, and position errors is proposed. Unlike traditional calibration methods for antenna array, the proposed method can be used in the broadband and near-field signal model such as microphone array with arbitrary sensor geometries in one plane. Computer simulations are presented and simulation results show the new method having good performance.

Small-Space Microphone Array Fractional Delay Algorithm Based on FIR Filter for Cochlear Implant

Directional speech enhancement of signals from microphone arrays is an effective way to improve speech recognition for cochlear implant users. The strict implant size limitation results in a short distance between microphones. The fractional delay problem due to the short distance between microphones is solved by a maximal flat （Maxflat） finite impulse response （FIR） filter, using the Maxflat error criteria at a low frequency containing most of the speech information and energy. The fractional Maxfiat FIR filter approximates the ideal digital fractional filter at the magnitude response, phase response, and phase delay characteristics, and is also very low order. The results demonstrate that the Maxflat FIR filter accurately and effectively solves the fractional digital delay and is very suitable for real-time speech processing in practical cochlear implant products.

WALL PRESSURE FLUCTUATIONS OF TURBULENT FLOW OVER BACKWARD-FACING STEP WITH AND WITHOUT ENTRAINMENT: MICROPHONE ARRAY MEASUREMENT

Wall pressure fluctuations in turbulent boundary layer flow over backward-facing step with and without entrainment were investigated. Digital array pressure sensors and multi-arrayed microphones were employed to acquire the time-averaged static pressure and fluctuating pressure, respectively. The differences of two flows were scrutinized in terms of static pressure characteristics, pressure fluctuations, cross-correlation and coherence of wall pressure. Introduction of the entrainment increased scale of large-scale vortical structure and reduced its convection velocity. However, shedding frequency of large-scale vortical structures was found to be the same for both flows.

Landing noise of aircraft based on the fly-over measurements with a planar microphone array

A large planar microphone array, which consists of 111 microphones, was successfully developed. The positions of 111 microphones in the array were determined by a random optimization procedure for the largest possible amplification and dynamic range. The beam pattern of planar array was obtained by numerical calculation. This planar array was applied to measure a two-dimensional mapping of the sound sources on landing aircraft. It is shown that important airframe noise sources can be identified. The spectra and directivity of any interested noise source can also be obtained by this measurement.

A coherent method for finding arrival directions of speech signals and its application for noise reduction in microphone array

The research on finding the arrival directions of speech signals by microphone arrny is proposed. We first analyze the uniform microphone array and give the design for microphone array applied in the hand-free speech recognition. Combining the traditional direction finding technique of MUltiple SIgnal Classification (MUSIC) with the focusing matrix method, we improve the resolving power of the microphone array for multiple speech sources.As one application of finding Direction of Arrival (DOA), a new microphone-array system for noise reduction is proposed. The new system is based on maximum likelihood estimate technique which reconstruct superimposed signals from different directions by using DOA information. The DOA information is got in terms of focusing MUSIC method which has been proven to have high performance than conventional MUSIC method on speaker localization[1].

Sound Source Localization Based on SRP-PHAT Spatial Spectrum and Deep Neural Network

Microphone array-based sound source localization(SSL)is a challenging task in adverse acoustic scenarios.To address this,a novel SSL algorithm based on deep neural network(DNN)using steered response power-phase transform(SRP-PHAT)spatial spectrum as input feature is presented in this paper.Since the SRP-PHAT spatial power spectrum contains spatial location information,it is adopted as the input feature for sound source localization.DNN is exploited to extract the efficient location information from SRP-PHAT spatial power spectrum due to its advantage on extracting high-level features.SRP-PHAT at each steering position within a frame is arranged into a vector,which is treated as DNN input.A DNN model which can map the SRP-PHAT spatial spectrum to the azimuth of sound source is learned from the training signals.The azimuth of sound source is estimated through trained DNN model from the testing signals.Experiment results demonstrate that the proposed algorithm significantly improves localization performance whether the training and testing condition setup are the same or not,and is more robust to noise and reverberation.

A Robust and Efficient Compressed Sensing Algorithm for Wideband Acoustic Imaging

Wideband acoustic imaging,which combines compressed sensing(CS)and microphone arrays,is widely used for locating acoustic sources.However,the location results of this method are unstable,and the computational efficiency is low.In this work,in order to improve the robustness and reduce the computational cost,a DCS-SOMP-SVD compressed sensing method,which combines the distributed compressed sensing using simultaneously orthogonal matching pursuit(DCS-SOMP)and singular value decomposition(SVD)is proposed.The performance of the DCS-SOMP-SVD is studied through both simulation and experiment.In the simulation,the locating results of the DCS-SOMP-SVD method are compared with the wideband BP method and the DCS-SOMP method.In terms of computational efficiency,the proposed method is as efficient as the DCS-SOMP method and more efficient than the wideband BP method.In terms of locating accuracy,the proposed method can still locate all sources when the signal to noise ratio(SNR)is−20 dB,while the wideband BP method and the DCS-SOMP method can only locate all sources when the SNR is higher than 0 dB.The performance of the proposed method can be improved by expanding the frequency range.Moreover,there is no extra source in the maps of the proposed method,even though the target sparsity is overestimated.Finally,a gas leak experiment is conducted to verify the feasibility of the DCS-SOMP-SVD method in the practical engineering environment.The experimental results show that the proposed method can locate both two leak sources in different frequency ranges.This research proposes a DCS-SOMP-SVD method which has sufficient robustness and low computational cost for wideband acoustic imaging.

About Multichannel Speech Signal Extraction and Separation Techniques

The extraction of a desired speech signal from a noisy environment has become a challenging issue. In the recent years, the scientific community has particularly focused on multichannel techniques which are dealt with in this review. In fact, this study tries to classify these multichannel techniques into three main ones: Beamforming, Independent Component Analysis (ICA) and Time Frequency (T-F) masking. This paper also highlights their advantages and drawbacks. However these previously mentioned techniques could not afford satisfactory results. This fact leads to the idea that a combination of those techniques, which is depicted along this study, may probably provide more efficient results. Indeed, giving the fact that those approaches are still be considered as being not totally efficient, has led us to review these mentioned above in the hope that further researches will provide this domain with suitable innovations.