Paper: | SP-P2.5 | ||
Session: | Speaker Adaptation | ||
Time: | Tuesday, May 18, 13:00 - 15:00 | ||
Presentation: | Poster | ||
Topic: | Speech Processing: Adaptation/Normalization | ||
Title: | FEATURE SPACE GAUSSIANIZATION | ||
Authors: | George Saon; IBM T. J. Watson Research Center | ||
Satya Dharanipragada; IBM T. J. Watson Research Center | |||
Daniel Povey; IBM T. J. Watson Research Center | |||
Abstract: | We propose a non-linear feature space transformation forspeaker/environment adaptation which forces the individual dimensions of the acoustic data for every speaker to be Gaussian distributed. The transformation is given by the preimage under the Gaussian cumulative distribution function (CDF) of the empirical CDF on a per dimension basis. We show that, for a given dimension, this transformation achieves minimum divergence between the density function of the transformed adaptation data and the normal density with zero mean and unit variance. Experimental results on both small and large vocabulary tasks show consistent improvements over the application of linearadaptation transforms only. | ||
Back |
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops