SRI's 2004 NIST Speaker Recognition Evaluation System

Published 11 October 2006

Sachin Kajarekar, Luciana Ferrer, E. Shriberg, Kemal Sönmez, Andreas Stolcke, Anand Venkataraman

DOI10.1109/icassp.2005.1415078

Citations50

TL;DR

A system that uses discriminant features from cepstral coefficients, and systems that use discriminant models from word n-grams and syllable-based NERF n- grams together with a cEPstral baseline system are evaluated.

Abstract

The paper describes our recent efforts in exploring longer-range features and their statistical modeling techniques for speaker recognition. In particular, we describe a system that uses discriminant features from cepstral coefficients, and systems that use discriminant models from word n-grams and syllable-based NERF n-grams. These systems together with a cepstral baseline system are evaluated on the 2004 NIST speaker recognition evaluation dataset. The effect of the development set is measured using two different datasets, one from Switchboard databases and another from the FISHER database. Results show that the difference between the development and evaluation sets affects the performance of the systems only when more training data is available. Results also show that systems using longer-range features combined with the baseline result in about a 31% improvement with 1-side training over the baseline system and about a 61% improvement with 8-side training over the baseline system.

Keywords

Computer Science

The Nature of Statistical Learning Theory

39,279 Citations1995Vladimir Vapnik

Digital Signal ProcessingSpeaker Verification Using Adapted Gaussian Mixture Models

4,268 Citations2000Douglas A. Reynolds, Thomas F. Quatieri +1 more

The major elements of MIT Lincoln Laboratory's Gaussian mixture model (GMM)-based speaker verification system used successfully in several NIST Speaker Recognition Evaluations (SREs) are described.

IEEE Transactions on Speech and Audio ProcessingSemi-tied covariance matrices for hidden Markov models

538 Citations1999Mark Gales

A new form of covariance matrix which allows a few "full" covariance matrices to be shared over many distributions, whilst each distribution maintains its own "diagonal" covariancy matrix is introduced.

2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).Channel robust speaker verification via feature mapping

229 Citations2003D.A. Reynolds

A new feature mapping technique that maps feature vectors into a channel independent space is presented that learns mapping parameters from a set of channel-dependent models derived from a channel-independent model via MAP adaptation.

THE SRI MARCH 2000 HUB-5 CONVERSATIONAL SPEECH TRANSCRIPTION SYSTEM

148 Citations2000Andreas Stolcke, Harry Bratt +7 more

SRI’s large vocabulary conversational speech r ecognition system as used in the March 2000 NIST Hub-5E evaluation is described and a generalized ROVER algorithm is applied to combine the N-best hypotheses from several systems based on different acoustic models.

Modeling duration patterns for speaker recognition

51 Citations2003Luciana Ferrer, Harry Bratt +6 more

This work presents a method for speaker recognition that uses the duration patterns of speech units to aid speaker classification and finds that this approach yields significant perfomance improvement when combined with a state-of-the-art speaker recognition system based on standard cepstral features.

Modeling NERFs for speaker recognition.

23 Citations2004Sachin Kajarekar, Luciana Ferrer +4 more

This paper proposes three methods for modeling NERFs that cope with missing features and shows that on the 2003 NIST extended-data speaker recognition evaluation task, a NERF system yields an EER of 11.6% alone, and improves the MFCC baseline performance by roughly 15% relative.

SVM modeling of "SNERF-grams" for speaker recognition

21 Citations2004Elizabeth Shriberg, Luciana Ferrer +2 more

Results show that SNERF-grams provide significant performance gains when combined with a state-of-the-art baseline syst em, as well as with both prosodic and word-based noncepstral systems.