Fig. 7From: Front-end technologies for robust ASR in reverberant environments—spectral enhancement-based dereverberation and auditory modulation filterbank featuresASR performance of AMFB features with GMM-HMM for Dev. The SE algorithm (dashed lines), MVN, and a trigram LM are used for evaluation. MFCC-LDA-MLLT features are employed as baseline for comparisonBack to article page