Comparing noise compensation methods for robust prediction of acoustic speech features from MFCC vectors in noise

Ben Milner, Jonathan Darch, Ibrahim Almajai, Saeed Vaseghi

Research output: Contribution to conferencePaper

4 Citations (Scopus)


The aim of this paper is to investigate the effect of applying noise compensation methods to acoustic speech feature prediction from MFCC vectors, as may be required in a distributed speech recognition (DSR) architecture. A brief review is made of maximum a posteriori (MAP) prediction of acoustic features from MFCC vectors using both global and phoneme-specific modeling of speech. The application of spectral subtraction and model adaptation to MAP acoustic feature prediction is then introduced. Experimental results are presented to compare the effect of noise compensation on acoustic feature prediction accuracy using both the global and phoneme-specific systems. Results across a range of signal-to-noise ratios show model adaptation to be better than spectral subtraction and able to restore performance close to that achieved in matched training and testing
Original languageEnglish
Publication statusPublished - 2008
Event16th European Signal Processing Conference - Lausanne, Switzerland
Duration: 25 Aug 200829 Aug 2008


Conference16th European Signal Processing Conference
Abbreviated titleEUSIPCO 2008

Cite this