8th European Conference on Speech Communication and Technology

Geneva, Switzerland
September 1-4, 2003


Robust Speech Recognition Using Missing Feature Theory in the Cepstral or LDA Domain

Hugo van Hamme

Katholieke Universiteit Leuven, Belgium

When applying Missing Feature Theory to noise robust speech recognition, spectral features are labeled as either reliable or unreliable in the time-frequency plane. The acoustic model evaluation of the unreliable features is modified to express that their clean values are unknown or confined within bounds. Classically, MFT requires an assumption of statistical independence in the spectral domain, which deteriorates the accuracy on clean speech. In this paper, MFT is expressed in any domain that is a linear transform of (log-)spectra, for example for cepstra and their time-derivatives. The acoustic model evaluation is recast as a nonnegative least squares problem. Approximate solutions are proposed and the success of the method is shown through experiments on the AURORA-2 database.

Full Paper

Bibliographic reference.  Hamme, Hugo van (2003): "Robust speech recognition using missing feature theory in the cepstral or LDA domain", In EUROSPEECH-2003, 3089-3092.