Afsaneh Asaei (co-advised; 2013)

Research Interests:

  • Array signal processing
  • Sparse component analysis
  • Statistical pattern recognition

Biography

Afsaneh Asaei received her B.Sc. in Electrical Engineering from Amirkabir University of Technology and M.Sc. (Hons.) in Computer Engineering from Sharif University of Technology. She was a Fellow of Marie Curie on Speech Communication with Adaptive LEarning (SCALE) project and obtained her PhD from Ecole Polytechnique Fédérale de Lausanne (EPFL) in 2013. Her research interests include signal processing, machine learning and sparse signal recovery and acquisition. Her PhD theses entitled Model-based Sparse Component Analysis for Multiparty Distant Speech Recognition was supervised by Professor Bourlard and co-advised by Professor Cevher.

Publications with LIONS (most recent)

Binary Sparse Coding of Convolutive Mixtures for Sound Localization and Separation via Spatialization

A. Asaei; M. Taghizadeh; S. Haghighatshoar; B. Raj; H. Bourlard et al. 

Ieee Transactions On Signal Processing. 2016. Vol. 64, num. 3, p. 567-579. DOI : 10.1109/Tsp.2015.2488598.

Computational Methods for Underdetermined Convolutive Speech Localization and Separation via Model-based Sparse Component Analysis

A. Asaei; H. Bourlard; M. J. Taghizadeh; V. Cevher 

Speech Communication. 2016. Vol. 76, p. 201-217. DOI : 10.1016/j.specom.2015.07.002.

Model-based Sparse Component Analysis for Reverberant Speech Localization

A. Asaei; H. Bourlard; M. Taghizadeh; V. Cevher 

2014. IEEE International Conference on Acoustics, Speech and Signal Processing, Florence, Italy, May 4-9. p. 1439-1443. DOI : 10.1109/ICASSP.2014.6853835.

Structured Sparsity Models for Reverberant Speech Separation

A. Asaei; M. Golbabaee; H. Bourlard; V. Cevher 

IEEE Transactions on Audio, Speech and Language Processing. 2014. Vol. 22, num. 3, p. 620-633. DOI : 10.1109/Taslp.2013.2297012.

Structured Sparse Acoustic Modeling for Speech Separation

A. Asaei; M. Golbabaee; H. Bourlard; V. Cevher 

2013. Signal Processing with Adaptive Sparse Structured Representations SPARS.