Browse > Article

Robust Feature Normalization Scheme Using Separated Eigenspace in Noisy Environments  

Lee Yoonjae (고려대학교 전자컴퓨터공학과)
Ko Hanseok (고려대학교 전자컴퓨터공학과)
Abstract
We Propose a new feature normalization scheme based on eigenspace for achieving robust speech recognition. In general, mean and variance normalization (MVN) is Performed in cepstral domain. However, another MVN approach using eigenspace was recently introduced. in that the eigenspace normalization Procedure Performs normalization in a single eigenspace. This Procedure consists of linear PCA matrix feature transformation followed by mean and variance normalization of the transformed cepstral feature. In this method. 39 dimensional feature distribution is represented using only a single eigenspace. However it is observed to be insufficient to represent all data distribution using only a sin91e eigenvector. For more specific representation. we apply unique na independent eigenspaces to cepstra, delta and delta-delta cepstra respectively in this Paper. We also normalize training data in eigenspace and get the model from the normalized training data. Finally. a feature space rotation procedure is introduced to reduce the mismatch of training and test data distribution in noisy condition. As a result, we obtained a substantial recognition improvement over the basic eigenspace normalization.
Keywords
Speech recognition; Mean and variance normalization; Separated eigenspace; Feature space rotation;
Citations & Related Records
연도 인용수 순위
  • Reference
1 A. Vinciarelli and S. Bengio 'Offline Cursive Word Recognition using Continuous Density Hidden Markov Models trained with PCA or ICA Features', Proc. of 16th International Conference on Pattern Recognition, 3, 81-84, 2002
2 Sirko Molau, Daniel Keysers and Hermann Ney, 'Matching Training and Test data Distributions for Robust Speech Reconnition', Speech Communication, 41 (4), 579-601, 2003   DOI   ScienceOn
3 H. G. Hirsch and D.Pearce, 'The AURORA Experimental Framework for the Performance Evaluations of Speech Recognition Systems under Noisy Conditions', ISCA ITRW ASR2000, 2000
4 P. Jain and H. Hermansky, 'Improved Mean and Variance Normalization for Robust Speech Recognition', Proc. of ICASSP, 2001
5 ETSI standard document, Speech Processing, Transmission and Quality aspects (STQ); Distributed speech recognition; Front-end feature extraction algorithm; Compression algorithms, ETSI ES 201 108 v1.1.3 (2000-04), 2000
6 X. Huang, A. Acero and H. Hon, Spoken Language Processing, (Prentice Hall PTR, 2001)
7 Kaisheng Yao, Erik Visser, Oh-Wook Kwon, and Te-Won Lee, 'A Speech Processing Front-End with Eigenspace Normalization for Robust Speech Reconition in Noisy Automobile Environments', Eurospeech 2003, 9-12, 2003