000192315 001__ 192315
000192315 005__ 20190316235756.0
000192315 0247_ $$2doi$$a10.1109/ICASSP.2011.5947379
000192315 037__ $$aCONF
000192315 245__ $$aModel-based Compressive Sensing for Multi-party Distant Speech Recognition
000192315 269__ $$a2011
000192315 260__ $$c2011
000192315 336__ $$aConference Papers
000192315 520__ $$aWe 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.
000192315 6531_ $$aModel-Based Compressive Sensing
000192315 6531_ $$aOverlapping Speech
000192315 6531_ $$aSparse Component Analysis
000192315 6531_ $$aSparse Recovery
000192315 6531_ $$aspeech recognition
000192315 700__ $$0243353$$g188259$$aAsaei, Afsaneh
000192315 700__ $$g117014$$aBourlard, Hervé$$0243348
000192315 700__ $$aCevher, Volkan
000192315 7112_ $$dMay 22-27, 2011$$cPrague, Czech Republic$$a2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
000192315 8564_ $$uhttp://publications.idiap.ch/index.php/publications/showcite/Asaei_Idiap-RR-04-2011$$zURL
000192315 8564_ $$uhttps://infoscience.epfl.ch/record/192315/files/Asaei_ICASSP_2011.pdf$$zn/a$$s147019$$yn/a
000192315 909C0 $$xU10381$$0252189$$pLIDIAP
000192315 909CO $$ooai:infoscience.tind.io:192315$$qGLOBAL_SET$$pconf$$pSTI
000192315 917Z8 $$x231598
000192315 937__ $$aEPFL-CONF-192315
000192315 970__ $$aAsaei_ICASSP_2011/LIDIAP
000192315 973__ $$rNON-REVIEWED$$sPUBLISHED$$aEPFL
000192315 980__ $$aCONF