INTERSPEECH 2008
9th Annual Conference of the International Speech Communication Association

Brisbane, Australia
September 22-26, 2008

A Phase-Averaged Model for the Relationship Between Noisy Speech, Clean Speech and Noise in the Log-Mel Domain

Friedrich Faubel, John McDonough, Dietrich Klakow

Saarland University, Germany

In this work, we demonstrate that the most widely-used model for the relationship between noisy speech, clean speech and noise in the log-Mel domain is inaccurate due to its disregard of the phase. Moreover, we show how a more exact model can be derived by averaging over the phase in the log-Mel domain, and how this can profitably be applied to particle filter based sequential noise compensation. Experimental results confirm the superiority of the phase-averaged model for both clean speech estimation in general and the particle filter in particular. Reductions in word error rate of up to 17% relative were obtained on a large vocabulary task.

Full Paper

Bibliographic reference.  Faubel, Friedrich / McDonough, John / Klakow, Dietrich (2008): "A phase-averaged model for the relationship between noisy speech, clean speech and noise in the log-mel domain", In INTERSPEECH-2008, 553-556.