Interspeech'2005 - Eurospeech

Lisbon, Portugal
September 4-8, 2005

Flavors of Gaussian Warping

Pierre Ouellet, Gilles Boulianne, Patrick Kenny

Centre de Recherche Informatique de Montréal, Canada

In recent years, speech recognition researchers have proposed the use of Gaussian warping as a step in the computation of input speech feature parameters. This warping is intended to reduce the mismatch between the actual statistical distribution of parameters and the distribution hypothesized in the acoustic models used, i.e., the Gaussian distribution. In this paper, we compare variants of Gaussianization, including off-line and windowed (short-term) versions, which we evaluate on a corpus of Canadian Parliamentary Debates.

Full Paper

Bibliographic reference.  Ouellet, Pierre / Boulianne, Gilles / Kenny, Patrick (2005): "Flavors of Gaussian warping", In INTERSPEECH-2005, 2957-2960.