logo Idiap Research Institute        
 [BibTeX] [Marc21]
Binary Sparse Coding of Convolutive Mixtures for Sound Localization and Separation via Spatialization
Type of publication: Journal paper
Citation: Asaei_IEEE-TSP_2015
Publication status: Published
Journal: IEEE Transactions on Signal Processing
Volume: 64
Number: 3
Year: 2016
Pages: 567-579
DOI: 10.1109/Tsp.2015.2488598
Abstract: We propose a sparse coding approach to address the problem of source-sensor localization and speech reconstruction. This approach relies on designing a dictionary of spatialized signals by projecting the microphone array recordings into the array manifolds characterized for different locations in a reverberant enclosure using the image model. Sparse representation over this dictionary enables identifying the subspace of the actual recordings and its correspondence to the source and sensor locations. The speech signal is reconstructed by inverse filtering the acoustic channels associated to the array manifolds. We provide rigorous analysis on the optimality of speech reconstruction by elucidating the links between inverse filtering and source separation followed by deconvolution. This procedure is evaluated for localization, reconstruction and recognition of simultaneous speech sources using real data recordings. The results demonstrate the effectiveness of the proposed approach and compare favorably against beamforming and independent component analysis techniques.
Projects Idiap
PHASER 200021-153507
Authors Asaei, Afsaneh
Taghizadeh, Mohammad J.
Haghighatshoar, Saeid
Raj, Bhiksha
Bourlard, Hervé
Cevher, Volkan
Added by: [UNK]
Total mark: 0
  • Asaei_IEEE-TSP_2015.pdf