New hos-based parameter estimation methods for speech recognition in noisy environments
Document typeConference report
Rights accessOpen Access
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
CitationMoreno, A., Tortola, S., Vidal, J., Fonollosa, José A. R. New hos-based parameter estimation methods for speech recognition in noisy environments. A: IEEE International Conference on Acoustics, Speech, and Signal Processing. "ICASSP 1995: IEEE International Conference on Acoustics, Speech and Signal Processing: May 9-12, 1995". Detroit, Michigan: . S.N., 1995, p. 429-432.