Model-Based Compressive Sensing for Multi-Party Distant Speech Recognition

We leverage the recent algorithmic advances in compressive sensing, and propose a novel source separation algorithm for efficient recovery of convolutive speech mixtures in spectro-temporal domain. Compared to the common sparse component analysis techniques, our approach fully exploits structured sparsity models to obtain substantial improvement over the existing state-of-the-art. We evaluate our method for separation and recognition of a target speaker in a multi-party scenario. Our results provide compelling evidence of the effectiveness of sparse recovery formulations in speech recognition.


Year:
2011
Publisher:
Idiap
Keywords:
Laboratories:




 Record created 2011-05-19, last modified 2018-09-13

n/a:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)