000083084 001__ 83084
000083084 005__ 20181114202019.0
000083084 037__ $$aCONF
000083084 245__ $$aPhase AutoCorrelation (PAC) features in Entropy based Multi-Stream for Robust Speech Recognition
000083084 269__ $$a2004
000083084 260__ $$aMontreal, Canada$$c2004
000083084 336__ $$aConference Papers
000083084 520__ $$aMethods to improve noise robustness of speech recognition systems often result in degradation of recognition performance for clean speech. Recently proposed Phase AutoCorrelation (PAC) \cite{ikbal03,ikbal03a} based features, showing noticeable improvement in noise robustness, also suffer from this draw back. In this paper, we try to alleviate this problem by using the PAC based features along with regular speech features in a multi-stream framework. The multi-stream system uses entropy of the posterior probability distribution, computed during recognition, as a confidence measure to adaptively combine evidences from different feature streams \cite{misra03}. Experimental results obtained on OGI Numbers95 database and Noisex92 noise database show that such a system yields best possible recognition performance in all conditions. Actually, the combination always performs better than the best performing stream for all the conditions.
000083084 6531_ $$aspeech
000083084 6531_ $$aikbal
000083084 6531_ $$amisra
000083084 6531_ $$abourlard
000083084 6531_ $$ahynek
000083084 700__ $$aIkbal, Shajith
000083084 700__ $$aMisra, Hemant
000083084 700__ $$0243348$$aBourlard, Hervé$$g117014
000083084 700__ $$0241097$$aHermansky, Hynek$$g154878
000083084 7112_ $$aProceedings of the 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-04)
000083084 773__ $$tProceedings of the 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-04)
000083084 8564_ $$uhttp://publications.idiap.ch/downloads/reports/2003/rr03-54.pdf$$zURL
000083084 8564_ $$uhttp://publications.idiap.ch/index.php/publications/showcite/ikbal-rr-03-54$$zRelated documents
000083084 8564_ $$s219732$$uhttps://infoscience.epfl.ch/record/83084/files/rr03-54.pdf$$zn/a
000083084 909C0 $$0252189$$pLIDIAP$$xU10381
000083084 909CO $$ooai:infoscience.tind.io:83084$$pconf$$pSTI$$qGLOBAL_SET
000083084 937__ $$aEPFL-CONF-83084
000083084 970__ $$aikbal-rr-03-54p/LIDIAP
000083084 973__ $$aEPFL$$sPUBLISHED
000083084 980__ $$aCONF