000197357 001__ 197357
000197357 005__ 20190316235848.0
000197357 037__ $$aCONF
000197357 245__ $$aModel-based Sparse Component Analysis for Reverberant Speech Localization
000197357 269__ $$a2014
000197357 260__ $$c2014
000197357 336__ $$aConference Papers
000197357 520__ $$aIn this paper, the problem of multiple speaker localization via speech separation based on model-based sparse recovery is studies. We compare and contrast computational sparse optimization methods incorporating harmonicity and block structures as well as autoregressive dependencies underlying spectrographic representation of speech signals. The results demonstrate the effectiveness of block sparse Bayesian learning framework incorporating autoregressive correlations to achieve a highly accurate localization performance. Furthermore, significant improvement is obtained using ad-hoc microphones for data acquisition set-up compared to the compact microphone array.
000197357 6531_ $$aStructured sparsity
000197357 6531_ $$aReverberant speech localization
000197357 6531_ $$aAutoregressive modeling
000197357 6531_ $$aAd hoc microphone array
000197357 700__ $$0243353$$g188259$$aAsaei, Afsaneh
000197357 700__ $$0243348$$g117014$$aBourlard, Hervé
000197357 700__ $$g193629$$aTaghizadeh, Mohammadjavad$$0246036
000197357 700__ $$g199128$$aCevher, Volkan$$0243957
000197357 7112_ $$dMay 4-9$$cFlorence, Italy$$aIEEE International Conference on Acoustics, Speech and Signal Processing
000197357 8564_ $$uhttps://infoscience.epfl.ch/record/197357/files/ICASSP.pdf$$zn/a$$s251408$$yn/a
000197357 909C0 $$xU12179$$0252306$$pLIONS
000197357 909C0 $$pLIDIAP$$xU10381$$0252189
000197357 909CO $$qGLOBAL_SET$$pconf$$pSTI$$ooai:infoscience.tind.io:197357
000197357 917Z8 $$x188259
000197357 937__ $$aEPFL-CONF-197357
000197357 973__ $$rREVIEWED$$sACCEPTED$$aEPFL
000197357 970__ $$aAsaei_ICASSP_2014/IDIAP
000197357 980__ $$aCONF