Frequency map selection using a RBFN-based classifier in the MVDR beamformer for speaker localization in reverberant rooms

We present the weighted minimum variance distortionless response (WMVDR), which is a steered response power (SRP) algorithm, for near-field speaker localization in a reverberant environment. The proposed WMVDR is based on a machine learning approach for computing the incoherent frequency fusion of narrowband power maps. We adopt a radial basis function network (RBFN) classifier for the estimation of the weighting coefficients, and a marginal distribution of narrowband power map as feature for the supervised training operation. Simulations demonstrate the effectiveness of the proposed approach in different conditions.

[1]  Jörn Anemüller,et al.  A discriminative learning approach to probabilistic acoustic source localization , 2014, 2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC).

[2]  Parhi,et al.  Wideband DOA Estimation Algorithms for Multiple Moving Sources using Unattended Acoustic Sensors , 2008 .

[3]  Emanuel A. P. Habets,et al.  Geometry-Based Spatial Sound Acquisition Using Distributed Microphone Arrays , 2013, IEEE Transactions on Audio, Speech, and Language Processing.

[4]  Anthony G. Constantinides,et al.  Audio–Visual Active Speaker Tracking in Cluttered Indoors Environments , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[5]  Hong Wang,et al.  Coherent signal-subspace processing for the detection and estimation of angles of arrival of multiple wide-band sources , 1985, IEEE Trans. Acoust. Speech Signal Process..

[6]  Sergio Canazza,et al.  Adaptive Time Delay Estimation Using Filter Length Constraints for Source Localization in Reverberant Acoustic Environments , 2013, IEEE Signal Processing Letters.

[7]  Kazuya Takeda,et al.  Binaural sound localization for untrained directions based on a Gaussian mixture model , 2008, 2008 16th European Signal Processing Conference.

[8]  David S. Broomhead,et al.  Multivariable Functional Interpolation and Adaptive Networks , 1988, Complex Syst..

[9]  Daniele Salvati,et al.  Incident Signal Power Comparison for Localization of Concurrent Multiple Acoustic Sources , 2014, TheScientificWorldJournal.

[10]  Carlo Drioli,et al.  Incoherent Frequency Fusion for Broadband Steered Response Power Algorithms in Noisy Environments , 2014, IEEE Signal Processing Letters.

[11]  Raffaele Parisi,et al.  WAVES: weighted average of signal subspaces for robust wideband direction finding , 2001, IEEE Trans. Signal Process..

[12]  James H. McClellan,et al.  TOPS: new DOA estimator for wideband signals , 2006, IEEE Transactions on Signal Processing.

[13]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

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

[15]  Climent Nadeu,et al.  Multispeaker Localization and Tracking in Intelligent Environments , 2007, CLEAR.

[16]  J. Capon.  High-resolution frequency-wavenumber spectrum analysis , 1969 .

[17]  Kalpathi R. Subramanian,et al.  Interpolating implicit surfaces from scattered surface data using compactly supported radial basis functions , 2001, Proceedings International Conference on Shape Modeling and Applications.

[18]  Sharon Gannot,et al.  Relative transfer function modeling for supervised source localization , 2013, 2013 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics.

[19]  Henry Cox,et al.  Robust adaptive beamforming , 2005, IEEE Trans. Acoust. Speech Signal Process..