Low-resource noise-robust feature post-processing on Aurora 2.0

We present a highly effective and extremely simple noiserobust front end based on novel post-processing of standard MFCC features. It performs remarkably well on the Aurora 2.0 noisydigits database without requiring any increase in model complexity. Compared to the Aurora 2.0 baseline system, our technique improves the average word error rate by 45% in the multicondition training case, (matched training/testing conditions) and 60% in the clean training case (mismatched training/testing conditions) — this is an improvement that rivals some of the best known results on this database. Our method, moreover, improves the performances in all cases, regardless of clean or noisy speech, matched or mis-matched environments. Our technique is entirely general because it makes no assumptions about the existence, type, or level of noise in the speech signal. Moreover, its simplicity means that it should be easy to integrate with other techniques in order to yield further improvements.