New HOS-based parameter estimation methods for speech recognition in noisy environments

The problem of recognition in noisy environments is addressed. Often, a recognition system is used in a noisy environment and there is no possibility of training it with noisy samples. Classical speech analysis techniques are based on second-order statistics and their performance dramatically decreases when noise is present in the signal under analysis. New methods based on higher order statistics (HOS) are applied in a recognition system and compared against the autocorrelation method. Cumulant-based methods show better performance than autocorrelation-based methods for low SNR.