000082476 001__ 82476
000082476 005__ 20190124064600.0
000082476 037__ $$aREP_WORK
000082476 245__ $$aSubband-Based Speech Recognition in Noisy Conditions: The Full Combination Approach
000082476 269__ $$a1998
000082476 260__ $$bIDIAP$$c1998
000082476 336__ $$aReports
000082476 500__ $$aIDIAP-RR 98-15
000082476 520__ $$aIn this report, we investigate and compare different subband-based Automatic Speech Recognition (ASR) approaches, including an original approach, referred to as the ``full combination approach'', based on an estimate of the (noise-) weighted sum of posterior probabilities for all possible subband combinations. We show that the proposed estimate is a good approximation of the ideal, but often unpractical, solution consisting in explicitly considering all possible subband subsets. This approximation results in a nonlinear, still simple and easy to implement, combination function. As opposed to other subband-based approaches, we believe that the proposed solution is more optimal (mathematically correct) and allows us to relax some of the (subband) independence assumptions. Similarly to this full posterior combination approach, which combines the subbands after independent processing, a full feature combination approach is investigated, in which all the possible subband features are orthogonalized and combined into a single feature vector (before probability estimation). The different approaches have been tested and compared on the Numbers'95 database (free format numbers) with different levels of (Noisex'92) car noise. This was done on the basis of two different acoustic features, namely PLP and J-RASTA-PLP features, and different weighting schemes. Those experiments show that the full combination approximation yields very good estimates of the actual full combination posteriors and that both approaches yield very good recognition performance.
000082476 6531_ $$asubbands
000082476 6531_ $$anoise
000082476 6531_ $$ahagen
000082476 6531_ $$amultiband
000082476 6531_ $$amorris
000082476 6531_ $$abourlard
000082476 6531_ $$aspeech
000082476 6531_ $$aNoise
000082476 6531_ $$aHMM/ANN-Hybrid
000082476 700__ $$aHagen, Astrid
000082476 700__ $$aMorris, Andrew
000082476 700__ $$0243348$$aBourlard, Hervé$$g117014
000082476 8564_ $$uhttp://publications.idiap.ch/downloads/reports/1998/rr98-15.pdf$$zURL
000082476 8564_ $$s400097$$uhttps://infoscience.epfl.ch/record/82476/files/rr98-15.pdf$$zn/a
000082476 909C0 $$0252189$$pLIDIAP$$xU10381
000082476 909CO $$ooai:infoscience.tind.io:82476$$pSTI$$pGLOBAL_SET$$preport
000082476 937__ $$aEPFL-REPORT-82476
000082476 970__ $$aHagen98-SBS/LIDIAP
000082476 973__ $$aEPFL$$sPUBLISHED
000082476 980__ $$aREPORT