PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

LDA based feature estimation methods for LVCSR
Janne Pylkkönen
In: Interspeech 2006, 17-21 Sep 2006, Pittsburgh PA, USA.

Abstract

Features that model temporal aspects of phonemes are important in speech recognition. One method is to use linear discriminant analysis (LDA) to find discriminative features from a spectro-temporal input formed by concatenating consecutive frames of short-time spectrum features. Others use e.g. neural networks to process longer span spectral segments to improve recognition accuracy. Still the most widely used method for including temporal cues is to augment the short-time spectral features with simple time derivatives. In this paper a new feature estimation method based on pairwise linear discriminants is presented. We compare it and some of its variants to traditional MFCC features and to LDA estimated features in a large vocabulary continuous speech recognition (LVCSR) task. The features obtained with the new estimation method show significant improvements in recognition accuracy over MFCC and LDA features.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Speech
ID Code:2506
Deposited By:Janne Pylkkönen
Deposited On:22 November 2006