A comparison of composite features under degraded speech in speaker recognition

Authors:
J. P. Openshaw;Z. P. Sun;J. S. Mason
Affiliations:
University College of Swansea, Swansea, UK;University College of Swansea, Swansea, UK;University College of Swansea, Swansea, UK
Venue:
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II
Year:
1993

Citing 1
Cited 1

An investigation of PLP and IMELDA acoustic representations and of their potential for combination

ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference

Robust text-independent speaker identification using hybrid PCA&LDA

MICAI'06 Proceedings of the 5th Mexican international conference on Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper assesses a variety of features and their sensitivity to noise mis-match between the model and test noise conditions. We use speaker identification (SI) for a performance evaluation as this is very sensitive to feature changes, and propose a target for robustness in terms of matched noise conditions. Two primary features are considered MFCC and PLP, along with their RASTA and first order regression extensions. We find PLP-RASTA to give the best resilience under cross conditions for a single feature, and the LDA combination of MFCC and PLP-RASTA supplying the best performance overall. Only in combined training do we find satisfactory results for any feature.