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.

Fabrication of Silicon Condenser Microphone Using Oxidized Porous Silicon as Sacrificial Layer

A new technique to fabricate silicon condenser microphone is presented.The technique is based on the use of oxidized porous silicon as sacrificial layer for the air gap and the heavy p+-doping silicon of approximately 15μm thickness for the stiff backplate.The measured sensitivity of the microphone fabricated with this technique is in the range from -45dB(5.6mV/Pa) to -55dB(1.78mV/Pa) under the frequency from 500Hz to 10kHz,and shows a gradual increase at higher frequency.The cut-off frequency is above 20kHz.

光纤microphone的理论与实验研究

本文提出了一种新型的反射式光纤ｍｉｃｒｏｐｈｏｎｅ ，它把反射式光纤传感探头应用于传统的麦克风上，来实现对声波的调制．本文从理论和实验两方面给出了反射式光纤ｍｉｃｒｏｐｈｏｎｅ的光强调制函数，并对反射式光纤ｍｉｃｒｏｐｈｏｎｅ系统进行了研究．

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.

Modelling and Optimisation of a Spring-Supported Diaphragm Capacitive MEMS Microphone

Audio applications such as mobile communication and hearing aid devices demand a small size but high performance, stable and low cost microphone to reproduce a high quality sound. Capacitive microphone can be designed to fulfill such requirements with some trade-offs between sensitivity, operating frequency range, and noise level mainly due to the effect of device structure dimensions and viscous damping. Smaller microphone size and air gap will gradually decrease its sensitivity and increase the viscous damping. The aim of this research was to develop a mathematical model of a spring-supported diaphragm capacitive MEMS microphone as well as an approach to optimize a microphone’s performance. Because of the complex shapes in this latest type of diaphragm design trend, analytical modelling has not been previously attempted. A novel diaphragm design is proposed that offers increased mechanical sensitivity of a capacitive microphone by reducing its diaphragm stiffness. A lumped element model of the spring-supported diaphragm microphone is developed to analyze the complex relations between the microphone performance factors and to find the optimum dimensions based on the design requirements. It is shown analytically that the spring dimensions of the spring-supported diaphragm do not have large effects on the microphone performance com pared to the diaphragm and backplate size, diaphragm thickness, and air-gap distance. A 1 mm2 spring-supported diaphragm microphone is designed using several optimized performance parameters to give a –3 dB operating bandwidth of 10.2 kHz, a sensitivity of 4.67 mV/Pa (–46.5 dB ref. 1 V/Pa at 1 kHz using a bias voltage of 3 V), a pull-in voltage of 13 V, and a thermal noise of –22 dBA SPL.

Source localization with minimum variance distortionless response for spherical microphone arrays

To improve localization accuracy, the spherical microphone arrays are used to capture high-order wavefield in- formation. For the far field sound sources, the array signal model is constructed based on plane wave decomposition. The spatial spectrum function is calculated by minimum variance distortionless response （MVDR） to scan the three-dimensional space. The peak values of the spectrum function correspond to the directions of multiple sound sources. A diagonal loading method is adopted to solve the ill-conditioned cross spectrum matrix of the received signals. The loading level depends on the alleviation of the ill-condition of the matrix and the accuracy of the inverse calculation. Compared with plane wave decomposition method, our proposed localization algorithm can acquire high spatial resolution and better estimation for multiple sound source directions, especially in low signal to noise ratio （SNR）.

Microphone Array Speech Enhancement Based on Tensor Filtering Methods

This paper proposes a novel microphone array speech denoising scheme based on tensor filtering methods including truncated HOSVD(High-Order Singular Value Decomposition), low rank tensor approximation and multi-mode Wiener filtering. Microphone array speech signal is represented in three-order tensor space with channel, time, and spectrum modes and then tensor filtering model can be designed to process the multiway array data. As to the first method, noise can be reduced through the truncated HOSVD which is a simple scheme in tensor processing. It is more accurate to find the lower-rank approximation of the three-order tensor with Tucker model. Then MDL(Minimum Description Length) criterion is used to estimate the optimal tensor rank in the second method. Further, multimode Wiener filtering approach upon tensor analysis can be considered as the spanning of one-mode wiener filtering. How to take advantages of tensor model to obtain a set of filters is the heart of the novel scheme. The performances of the proposed three approaches are evaluated with objective indexes and listening quality test. The experimental results indicate that the proposed tenor filtering methods have potential ability of retrieving the target signal from noisy microphone array signal and the multi-mode Wiener filtering method provides the best denoising results among the three ones.

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.

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.

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.

Posture Adjustment of Microphone Based on Image Recognition in Automatic Welding System

As the requirements of production process is getting higher and higher with the reduction of volume,microphone production automation become an urgent need to improve the production efficiency.The most important part is studied and a precise algorithm of calculating the deviation angle of four types microphones is proposed,based on the feature extraction and visual detection.Pretreatment is performed to achieve the real-time microphone image.Canny edge detection and typical feature extraction are used to distinguish the four types of microphones,categorizing them as type M1 and type M2.And Hough transformation is used to extract the image features of microphone.Therefore,the deviation angle between the posture of microphone and the ideal posture in 2Dplane can be achieved.Depending on the angle,the system drives the motor to adjust posture of the microphone.The final purpose is to realize the high efficiency welding of four different types of microphones.

智能音响中MEMS Microphone性能测试的实现过程

Microphone作为人机交互的重要传感器广泛应用于智能手机,智能手环,平板电脑及智能音响等智能设备中,特别是MEMS(Micro-Electro Mechanical System微机电系统)Microphone应用最为广泛。其优势在于体积小,受温度影响小,可使用SMT(Surface Mount Technology表面贴装技术)制造,能够承受无铅制程所用的回流焊温度。如何检测MEMS Microphone在经过高达260摄氏度的回流焊接及与机构件组装后的性能,成为电子制造生产过程中非常重要的一环。文章就智能音响中所用MEMS Microphone在焊接及机构组装后,Microphone性能的测试过程进行阐述研究。

Detecting Photoacoustic Signals of Sulfur Hexafluoride at Varying Microphone Positions

Photoacoustic spectroscopy was used to test the photoacoustic properties of sulfur hexafluoride, an optically thick and potent greenhouse gas. While exploring the photoacoustic effect of sulfur hexafluoride, the effects of the position of the microphone within a gas cell were determined. Using a 35 cm gas cell, microphones were positioned at 17.5 cm, the middle of the gas cell, 12.5 cm, 7.5 cm, and 2.5 cm from the window of the cell. From the photoacoustic signal produced for each resonance frequency at each microphone position, the effects of acoustic pressure produced at each position on the signal recorded were observed. This is the first study done by experimentation with the photoacoustic effect to show that standing waves have different amplitudes at different microphone positions.

Space discriminative function for microphone array robust speech recognition

Based on W-disjoint orthogonality of speech mixtures, a space d,scnmlnative tunetlon was proposer1 to enumerate and localize competing speakers in the surrounding environments. Then, a Wiener-like postfiherer was developed to adaptively suppress interferences. Experimental results with a hands-free speech recognizer under various SNR and competing speakers settings show that nearly 69 % error reduction can be obtained with a two-channel small aperture microphone array against the conventional single microphone baseline system. Comparisons were made against traditional delay-and-sum and Griffiths-Jim adaptive beamforming techniques to further assess the effectiveness of this method.

基于卷积神经网络的移动机器人声源定位方法综述

听觉系统是机器人感知周围环境信息的重要途径之一,精准有效地进行声源定位,可极大提高移动机器人的感知与决策能力。将声源定位应用于危险环境救援与巡检具有重要工程意义。随着深度学习的广泛应用,引入卷积神经网络(convolutional neural networks, CNNs)的声源定位效果显著改善。将移动机器人声源定位研究从网络架构与改进、声音特征类型、数据仿真与增强,以及多模态信息融合四个角度进行综合对比及分析,并对技术的应用提出思考与展望。

利用麦克风阵列的管道主动噪声控制方法

空调通风管道在运行时,内部出现的低频噪声很难通过包裹消音材料等被动式降噪方法消除.而在部署主动噪声控制时,会出现声反馈现象,影响降噪性能甚至造成控制系统的响应发散.针对这种声反馈现象,本文在分析其产生原因的基础上,将麦克风阵列作为前馈,对Duvall-Frost结构的线性约束最小方差波束成形算法加入预调向,提出了利用麦克风阵列的管道主动噪声控制方法,实现单方向拾取来自管道上游的噪声信号,避免声反馈带来的影响.并利用滤波器x最小均方误差(FxLMS)算法作为自适应控制算法,针对4种典型低频噪声,在真实管道环境下进行主动降噪实验.实验结果表明,相比不使用麦克风阵列的情况,本文提出的主动噪声控制方法能达到明显的降噪性能,且在稳定性方面取得较好结果.

麦克风阵列鲁棒频率不变波束形成算法

在实际应用中,频率不变波束形成器通常受到麦克风阵列失配误差的影响,因此提高频率不变波束形成器的鲁棒性具有重要意义。针对上述问题提出了一种约束优化模型,可以在保持频率不变波束形成的同时提高阵列的鲁棒性。首先设计目标波束图,考虑到差分麦克风阵列本身具有频率不变的波束图,选用传统二阶超心型差分麦克风波束图做为目标波束图。上述模型以麦克风阵列权矢量的二范数作为目标函数来最大化鲁棒性,在无失真约束,目标波束主瓣逼近约束以及旁瓣增益精准控制约束下实现频率不变。然后在交替方向乘子法算法框架下,将优化问题分解为多个优化子问题求解,然后对每个优化子问题分别求解,通过仿真验证了在交替方向乘子法算法下上述模型的可行性与有效性,最终达到了麦克风阵列鲁棒频率不变波束响应的效果。

面向便携式野战医疗装备语音交互的小尺寸双麦前端系统设计

目的:针对野战噪声条件下便携式野战医疗装备的语音交互性能受到影响的问题,设计一种小尺寸双麦前端系统。方法:该系统基于最小二乘准则实现小尺寸双麦波速形成,进而实现前端语音增强。系统硬件主要由双麦、信号预处理模块、嵌入式处理器、模拟数字转换器(analog to digital converter,ADC)、数字模拟转换器(digital to analog converter,DAC)、供电模块等组成。其中,双麦采用2个贴片式微机电系统(micro electro mechanical system,MEMS)麦克风,信号预处理模块、ADC、DAC内置在通用音频编码器WM8978中,嵌入式处理器采用STM32F405系列处理器,供电模块采用LM1117电压调节器芯片。系统软件采用KeilμVision4开发软件编译和测试。为验证该系统的性能,进行指向性实验和语音增强实验。结果:指向性实验结果表明,在0.5~2.0 kHz频率范围内,该系统在各频点的指向性一致性较好;语音增强实验结果表明,在枪声、监护仪报警、医疗器皿碰撞3类非平稳噪声条件下,该系统可有效提升语音的音质及识别率。结论:该系统能实现语音增强,可为便携式野战医疗装备的语音交互提供有效的支持。