Computational methods for underdetermined convolutive speech localization and separation via model-based sparse component analysis
详细信息 查看全文
- 作者：Afsaneh Asaeia ; afsaneh.asaei@idiap.ch" class="auth_mail" title="E-mail the corresponding author ; Hervé ; Bourlarda ; b ; herve.bourlard@idiap.ch" class="auth_mail" title="E-mail the corresponding author ; Mohammad J. Taghizadeha ; b ; mohammad.taghizadeh@idiap.ch" class="auth_mail" title="E-mail the corresponding author ; Volkan Cevherb ; volkan.cevher@epfl.ch" class="auth_mail" title="E-mail the corresponding author
- 关键词：Structured sparse representation ; Model-based sparse recovery ; Reverberation ; Source localization and separation ; Sparse component analysis ; Computational auditory scene analysis
- 刊名：Speech Communication
- 出版年：2016
- 出版时间：February 2016
- 年：2016
- 卷：76
- 期：Complete
- 页码：201-217
- 全文大小：785 K
文摘
- •
Model-based sparse component analysis exploits structured sparsity for source separation.
- •
Spectral sparsity structures are formulated upon the principles of auditory scene analysis.
- •
Spatial sparsity structures are formulated upon the image model of multipath propagation.
- •
Performance of greedy, convex and Bayesian sparse recovery are evaluated.
- •
Ad hoc microphone arrays may lead to significant improvement in SCA performance.