Text-independent speaker recognition using graph matching

Authors:
Ville Hautamäki;Tomi Kinnunen;Pasi Fränti
Affiliations:
Speech and Image Processing Unit, Department of Computer Science and Statistics, University of Joensuu, P.O. Box 111, FI-80101, Joensuu, Finland;Speech and Image Processing Unit, Department of Computer Science and Statistics, University of Joensuu, P.O. Box 111, FI-80101, Joensuu, Finland;Speech and Image Processing Unit, Department of Computer Science and Statistics, University of Joensuu, P.O. Box 111, FI-80101, Joensuu, Finland
Venue:
Pattern Recognition Letters
Year:
2008

Citing 5
Cited 5

A graph distance metric based on the maximal common subgraph

Pattern Recognition Letters
On the Approximability of the Maximum Common Subgraph Problem

STACS '92 Proceedings of the 9th Annual Symposium on Theoretical Aspects of Computer Science
Fast Agglomerative Clustering Using a k-Nearest Neighbor Graph

IEEE Transactions on Pattern Analysis and Machine Intelligence
Explicit modelling of session variability for speaker verification

Computer Speech and Language
Speaker and Session Variability in GMM-Based Speaker Verification

IEEE Transactions on Audio, Speech, and Language Processing

An overview of text-independent speaker recognition: From features to supervectors

Speech Communication
Environmental robust speech and speaker recognition through multi-channel histogram equalization

Neurocomputing
Biometric identification based on the eye movements and graph matching techniques

Pattern Recognition Letters
Is masking a relevant aspect lacking in MFCC? A speaker verification perspective

Pattern Recognition Letters
Near-duplicate document image matching: A graphical perspective

Pattern Recognition

Quantified Score

Hi-index	0.10

Visualization

Abstract

Technical mismatches between the training and matching conditions adversely affect the performance of a speaker recognition system. In this paper, we present a matching scheme which is invariant to feature rotation, translation and uniform scaling. The proposed approach uses a neighborhood graph to represent the global shape of the feature distribution. The reference and test graphs are aligned by graph matching and the match score is computed using conventional template matching. Experiments on the NIST-1999 SRE corpus indicate that the method is comparable to conventional Gaussian mixture model (GMM) and vector quantization (VQ)-based approaches.