A DCT-based fast signal subspace technique for robust speech recognition

Author

Huang, Jun ; Zhao, Yunxin

Author_Institution

Beckman Inst. for Adv. Sci. & Technol., Illinois Univ., Urbana, IL, USA

Volume

8

Issue

6

fYear

2000

fDate

11/1/2000 12:00:00 AM

Firstpage

747

Lastpage

751

Abstract

In this correspondence, a fast computational method is proposed to approximate the Karhunen-Loeve transform (KLT) for the covariance matrix of the autoregressive process. A fast algorithm which reduces the computation of eigenvalues of an N×N symmetric Toeplitz matrix from O(N³) in KLT to N² is further developed. Experimental results demonstrate that the performance of the fast algorithm is very close to the KLT in eigenvalue computation and in energy constrained signal subspace speech enhancement for speech recognition in a car environment

Keywords

Karhunen-Loeve transforms; Toeplitz matrices; autoregressive processes; covariance matrices; discrete cosine transforms; eigenvalues and eigenfunctions; speech enhancement; speech recognition; DCT-based fast signal subspace technique; KLT; Karhunen-Loeve transform; autoregressive process; car environment; covariance matrix; eigenvalues; energy constrained signal subspace speech enhancement; fast computational method; robust speech recognition; symmetric Toeplitz matrix; Covariance matrix; Discrete cosine transforms; Eigenvalues and eigenfunctions; Karhunen-Loeve transforms; Matrix decomposition; Robustness; Speech enhancement; Speech recognition; Subspace constraints; Symmetric matrices;

fLanguage

English

Journal_Title

Speech and Audio Processing, IEEE Transactions on

Publisher

ieee

ISSN

1063-6676

Type

jour

DOI

10.1109/89.876314

Filename

876314