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 s...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.展开更多
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 se...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.展开更多
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 cann...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.展开更多
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 ...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.展开更多
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 deve...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.展开更多
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 improv...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.展开更多
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 mic...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.展开更多
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 acqui...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.展开更多
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...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.展开更多
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 ...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].展开更多
Aiming at the problem that the traditional SRP-PHAT sound source localization method performs intensive search in a 360-degree space,resulting in high computational complexity and difficulty in meeting real-time requi...Aiming at the problem that the traditional SRP-PHAT sound source localization method performs intensive search in a 360-degree space,resulting in high computational complexity and difficulty in meeting real-time requirements,an innovative high-precision sound source localization method is proposed.This method combines the selective SRP-PHAT algorithm with real-time visual analysis.Its core innovations include using face detection to dynamically determine the scanning angle range to achieve visually guided selective scanning,distinguishing face sound sources from background noise through a sound source classification mechanism,and implementing intelligent background orientation selection to ensure comprehensive monitoring of environmental noise.Experimental results show that the method achieves a positioning accuracy of±5 degrees and a processing speed of more than 10FPS in complex real environments,and its performance is significantly better than the traditional full-angle scanning method.展开更多
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 transf...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.展开更多
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 efficien...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.展开更多
In order to overcome the obstacle of singular integral in boundary element method （BEM）, we presented an efficient sound field reconstruction technique based on the wave superposition method （WSM）. Its principle i...In order to overcome the obstacle of singular integral in boundary element method （BEM）, we presented an efficient sound field reconstruction technique based on the wave superposition method （WSM）. Its principle includes three steps： first, the sound pressure field of an arbitrary shaped radiator is measured with a microphone array; then, the exterior sound field of the radiator is computed backward and forward using the WSM; at last, the final results are visualized in terms of sound pressure contours or animations. With these visualized contours or animations, noise sources can be easily located and quantified; also noise transmission path can be found out. By numerical simulation and experimental results, we proved that the technique are suitable and accurate for sound field reconstruction. In addition, we presented a sound field reconstruction systern prototype on the basis of this technique. It makes a foundation for the application of wave superposition in the sound field reconstruction in industry situations.展开更多
Diagnosing wind turbine blade icing is crucial for enhancing the efficiency and reliability of wind power generation in cold regions.Current acoustic-based diagnostic techniques,while cost-efficient,face challenges in...Diagnosing wind turbine blade icing is crucial for enhancing the efficiency and reliability of wind power generation in cold regions.Current acoustic-based diagnostic techniques,while cost-efficient,face challenges in precision and signal processing within complex sound environments.For this reason,this paper proposes a new method for diagnosing blade icing,which includes an enhanced deep residual network based on densely connected modules and a data enhancement strategy to improve diagnostic results in complex environments.In particular,blade acoustic signatures,rich in spatial information,are captured using a microphone array.These signals are then processed by a model combining fixed-orientation delay-and-sum beamforming with the enhanced deep residual network.The performance of the proposed method for blade icing damage diagnosis has been evaluated through a 600 W wind turbine under different operating and measurement conditions,and experiments have been conducted under different blade icing positions.The results show that the proposed approach achieved high diagnostic precision,yielding F1-scores of 0.9354 and 0.9297.These scores indicate a substantial improvement in accurately identifying blade icing compared to existing other methods.Furthermore,the competitiveness of the proposed method is further demonstrated through ablation studies.This work makes an important contribution to the sustainable utilization of wind energy resources in cold regions.展开更多
The steered response power-phase transform (SRP-PHAT) sound source localization algorithm is robust in a real environment. However, the large computation complexity limits the practical application of SRP-PHAT. For a ...The steered response power-phase transform (SRP-PHAT) sound source localization algorithm is robust in a real environment. However, the large computation complexity limits the practical application of SRP-PHAT. For a microphone array, each location corresponds to a set of time differences of arrival (TDOAs), and this paper collects them into a TDOA vector. Since the TDOA vectors in the adjacent regions are similar, we present a fast algorithm based on clustering search to reduce the computation complexity of SRP-PHAT. In the training stage, the K-means or Iterative Self-Organizing Data Analysis Technique (ISODATA) clustering algorithm is used to find the centroid in each cluster with similar TDOA vectors. In the procedure of sound localization, the optimal cluster is found by comparing the steered response powers (SRPs) of all centroids. The SRPs of all candidate locations in the optimal cluster are compared to localize the sound source. Experiments both in simulation environments and real environments have been performed to compare the localization accuracy and computational load of the proposed method with those of the conventional SRP-PHAT algorithm. The results show that the proposed method is able to reduce the computational load drastically and maintains almost the same localization accuracy and robustness as those of the conventional SRP-PHAT algorithm. The difference in localization performance brought by different clustering algorithms used in the training stage is trivial.展开更多
基金F inancially supported by the Bundersministerium fur Bildung und Forschung ( BMBF) of Germ any
文摘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.
基金Supported by the National Natural Science Foundation of China(No.61201345)the Beijing Key Laboratory of Advanced Information Science and Network Technology(No.XDXX1308)
文摘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.
基金supported by Nature Science Research Project of Higher Education Institutions in Jiangsu Province under Grant No.21KJB510018National Nature Science Foundation of China (NSFC)under Grant No.62001215.
文摘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.
基金This work was supported by the Key Project of Science and Technology of Sichuan Province under Grant No. 04GG21-02-20.
文摘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.
文摘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.
基金This work is supported by Nanjing Institute of Technology(NIT)fund for Research Startup Projects of Introduced talents under Grant No.YKJ202019Nature Sci-ence Research Project of Higher Education Institutions in Jiangsu Province under Grant No.21KJB510018+1 种基金National Nature Science Foundation of China(NSFC)under Grant No.62001215NIT fund for Doctoral Research Projects under Grant No.ZKJ2020003.
文摘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.
基金Supported by the National Natural Science Foundation of China(Nos. 60871083 and 30800234)the Beijing Natural Science Foundation(No. 3082012)the Key Technologies R&D Program of Ministry of Science and Technology of the People’s Republic of China(No. 2008BAI50B08)
文摘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.
文摘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.
基金the Bundesministerium fur Bildung und Forschung (BMBF) of Germany.
文摘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.
文摘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].
基金the research result of the 2024 Guangxi Higher Education Undergraduate Teaching Reform Project“OBE-Guided,Digitally Empowered‘Hadoop Big Data Development Technology’Course Ideological and Political Construction Innovation Exploration and Practice”(Project No.:2024JGA396).
文摘Aiming at the problem that the traditional SRP-PHAT sound source localization method performs intensive search in a 360-degree space,resulting in high computational complexity and difficulty in meeting real-time requirements,an innovative high-precision sound source localization method is proposed.This method combines the selective SRP-PHAT algorithm with real-time visual analysis.Its core innovations include using face detection to dynamically determine the scanning angle range to achieve visually guided selective scanning,distinguishing face sound sources from background noise through a sound source classification mechanism,and implementing intelligent background orientation selection to ensure comprehensive monitoring of environmental noise.Experimental results show that the method achieves a positioning accuracy of±5 degrees and a processing speed of more than 10FPS in complex real environments,and its performance is significantly better than the traditional full-angle scanning method.
基金This work is supported by the National Nature Science Foundation of China(NSFC)under Grant No.61571106Jiangsu Natural Science Foundation under Grant No.BK20170757the Natural Science Foundation of the Jiangsu Higher Education Institutions of China under grant No.17KJD510002.
文摘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.
基金Supported by National Natural Science Foundation of China(Grant Nos.51675425,52075441)Shaanxi Provincial Key Research Program Project of China(Grant No.2020ZDLGY06-09)+1 种基金Dongguan Municipal Social Science and Technology Development(key)Project of China(Grant No.20185071021600)Science and Technology on Micro-system Laboratory Foundation of China(Grant No.6142804200405).
文摘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.
基金the National High Technology Re-search and Development Program (863) of China(2006AA04Z175)
文摘In order to overcome the obstacle of singular integral in boundary element method （BEM）, we presented an efficient sound field reconstruction technique based on the wave superposition method （WSM）. Its principle includes three steps： first, the sound pressure field of an arbitrary shaped radiator is measured with a microphone array; then, the exterior sound field of the radiator is computed backward and forward using the WSM; at last, the final results are visualized in terms of sound pressure contours or animations. With these visualized contours or animations, noise sources can be easily located and quantified; also noise transmission path can be found out. By numerical simulation and experimental results, we proved that the technique are suitable and accurate for sound field reconstruction. In addition, we presented a sound field reconstruction systern prototype on the basis of this technique. It makes a foundation for the application of wave superposition in the sound field reconstruction in industry situations.
基金supported by National Natural Science Foundation of China under Grant No 12064033,52376162。
文摘Diagnosing wind turbine blade icing is crucial for enhancing the efficiency and reliability of wind power generation in cold regions.Current acoustic-based diagnostic techniques,while cost-efficient,face challenges in precision and signal processing within complex sound environments.For this reason,this paper proposes a new method for diagnosing blade icing,which includes an enhanced deep residual network based on densely connected modules and a data enhancement strategy to improve diagnostic results in complex environments.In particular,blade acoustic signatures,rich in spatial information,are captured using a microphone array.These signals are then processed by a model combining fixed-orientation delay-and-sum beamforming with the enhanced deep residual network.The performance of the proposed method for blade icing damage diagnosis has been evaluated through a 600 W wind turbine under different operating and measurement conditions,and experiments have been conducted under different blade icing positions.The results show that the proposed approach achieved high diagnostic precision,yielding F1-scores of 0.9354 and 0.9297.These scores indicate a substantial improvement in accurately identifying blade icing compared to existing other methods.Furthermore,the competitiveness of the proposed method is further demonstrated through ablation studies.This work makes an important contribution to the sustainable utilization of wind energy resources in cold regions.
基金supported by the National Natural Science Foundation of China(Grant Nos. 60971098 and 61201345)the Beijing Key Laboratory of Advanced Information Science and Network Technology(Grant No.XDXX1308)
文摘The steered response power-phase transform (SRP-PHAT) sound source localization algorithm is robust in a real environment. However, the large computation complexity limits the practical application of SRP-PHAT. For a microphone array, each location corresponds to a set of time differences of arrival (TDOAs), and this paper collects them into a TDOA vector. Since the TDOA vectors in the adjacent regions are similar, we present a fast algorithm based on clustering search to reduce the computation complexity of SRP-PHAT. In the training stage, the K-means or Iterative Self-Organizing Data Analysis Technique (ISODATA) clustering algorithm is used to find the centroid in each cluster with similar TDOA vectors. In the procedure of sound localization, the optimal cluster is found by comparing the steered response powers (SRPs) of all centroids. The SRPs of all candidate locations in the optimal cluster are compared to localize the sound source. Experiments both in simulation environments and real environments have been performed to compare the localization accuracy and computational load of the proposed method with those of the conventional SRP-PHAT algorithm. The results show that the proposed method is able to reduce the computational load drastically and maintains almost the same localization accuracy and robustness as those of the conventional SRP-PHAT algorithm. The difference in localization performance brought by different clustering algorithms used in the training stage is trivial.
