Acoustic source localization in strong reverberant environment by parametric Bayesian dictionary learning

A parametric Bayesian dictionary learning approach is proposed for source localization problem under unknown strong reverberate environment. In particular, a parametric dictionary is constructed by discretizing the inner space of the enclosure, which formulates the reverberations as part of the signal model. Thereafter, the problem of localization can be considered as the sparse signal recovery and dictionary learning problem.In contrast to the conventional sparsity based source localization techniques, the dictionary is constructed in a parametric manner and will be updated during estimation in the proposed approach. Since unknown reverberations can be automatically estimated from the measurements by the proposed method, they can be appropriately exploited to enhance the accuracy of source localization.Since the proposed algorithm is constructed in a Bayesian framework, the proposed algorithm can able to obtain the capability of distinguishing highly correlated atoms in a dictionary, flexibility of modeling and capability of providing statistical information.Our simulated results have shown that the proposed algorithm can achieve high source localization accuracy, low sidelobes and high robustness for multiple sources with low computational complexity in strong reverberant environments compared with other state-of-the-art methods. Sparse representation techniques have become increasingly promising for localizing the sound source in reverberant environment, where the multipath channel effects can be accurately characterized by the image model. In this paper, a dictionary is constructed by discretizing the inner space of the enclosure, which is parameterized by the unknown energy reflective ratio. More specifically, each atom of the dictionary can characterize a specific source-to-microphone multipath channel. Subsequently, source localization can be reformulated as a joint sparse signal recovery and parametric dictionary learning problem. In particular, a sparse Bayesian framework is utilized for modeling, where its solution can be obtained by variational Bayesian expectation maximization technique. Moreover, the joint sparsity in frequency domain is exploited to improve the dictionary learning performances. A remarkably advantage of this approach is that no laborious parameter tuning procedure is required and statistical information can be provided. Numerical simulation results have shown that the proposed algorithm achieves high source localization accuracy, low sidelobes and high robustness for multiple sources with low computational complexity in strong reverberant environments, compared with other state-of-the-art methods.

[1]  Volkan Cevher,et al.  Model-based sparse component analysis for reverberant speech localization , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[2]  Emmanuel Vincent,et al.  Multi-source TDOA estimation in reverberant audio using angular spectra and clustering , 2012, Signal Process..

[3]  Laurent Daudet,et al.  Narrowband source localization in an unknown reverberant environment usingwavefield sparse decomposition , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[4]  Jacob Benesty,et al.  Broadband Music: Opportunities and Challenges for Multiple Source Localization , 2007, 2007 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics.

[5]  Rémi Gribonval,et al.  Beyond the Narrowband Approximation: Wideband Convex Methods for Under-Determined Reverberant Audio Source Separation , 2010, IEEE Transactions on Audio, Speech, and Language Processing.

[6]  Yonina C. Eldar,et al.  Block-Sparse Signals: Uncertainty Relations and Efficient Recovery , 2009, IEEE Transactions on Signal Processing.

[7]  Kazuhiro Nakadai,et al.  Sound source localization in spatially colored noise using a hierarchical Bayesian model , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[8]  Volkan Cevher,et al.  Model-Based Compressive Sensing , 2008, IEEE Transactions on Information Theory.

[9]  Jont B. Allen,et al.  Image method for efficiently simulating small‐room acoustics , 1976 .

[10]  Matthew J. Beal Variational algorithms for approximate Bayesian inference , 2003 .

[11]  Lawrence Carin,et al.  Bayesian Compressive Sensing , 2008, IEEE Transactions on Signal Processing.

[12]  Hiroshi Saruwatari,et al.  Sparse sound field decomposition using group sparse Bayesian learning , 2015, 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA).

[13]  Kazuhiro Nakadai,et al.  Sound Source Localization Using Joint Bayesian Estimation With a Hierarchical Noise Model , 2013, IEEE Transactions on Audio, Speech, and Language Processing.

[14]  Michael E. Tipping Sparse Bayesian Learning and the Relevance Vector Machine , 2001, J. Mach. Learn. Res..

[15]  D.G. Tzikas,et al.  The variational approximation for Bayesian inference , 2008, IEEE Signal Processing Magazine.

[16]  Lu Wang,et al.  Novel Wideband DOA Estimation Based on Sparse Bayesian Learning With Dirichlet Process Priors , 2016, IEEE Transactions on Signal Processing.

[17]  Volkan Cevher,et al.  Structured Sparsity Models for Reverberant Speech Separation , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[18]  Jonathan Le Roux,et al.  Source localization in reverberant environments using sparse optimization , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[19]  Aggelos K. Katsaggelos,et al.  Variational Bayesian Super Resolution , 2011, IEEE Transactions on Image Processing.

[20]  Shoichi Koyama,et al.  Sparse sound field representation in recording and reproduction for reducing spatial aliasing artifacts , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[21]  Benedikt Loesch,et al.  Comparison of Different Algorithms for Acoustic Source Localization , 2010, Sprachkommunikation.

[22]  Futoshi Asano,et al.  Joint estimation of sound source location and noise covariance in spatially colored noise , 2011, 2011 19th European Signal Processing Conference.

[23]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[24]  M. Yuan,et al.  Model selection and estimation in regression with grouped variables , 2006 .