Discriminative In-Set/Out-of-Set Speaker Recognition
- 22 January 2007
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech, and Language Processing
- Vol. 15 (2) , 498-508
Abstract
In this paper, the problem of identifying in-set versus out-of-set speakers for limited training/test data durations is addressed. The recognition objective is to form a decision regarding an input speaker as being a legitimate member of a set of enrolled speakers or outside speakers. The general goal is to perform rapid speaker model construction from limited enrollment and test size resources for in-set testing for input audio streams. In-set detection can help ensure security and proper access to private information, as well as detecting and tracking input speakers. Areas of applications of these concepts include rapid speaker tagging and tracking for information retrieval, communication networks, personal device assistants, and location access. We propose an integrated system with emphasis on short-enrollment data (about 5 s of speech for each enrolled speaker) and test data (2-8 s) within a text-independent mode. We present a simple and yet powerful decision rule to accept or reject speakers using a discriminative vector in the decision score space, together with statistical hypothesis testing based on the conventional likelihood ratio test. Discriminative training is introduced to further improve system performance for both decision techniques, by employing minimum classification error and minimum verification error frameworks. Experiments are performed using three separate corpora. Using the YOHO speaker recognition database, the alternative decision rule achieves measurable improvement over the likelihood ratio test, and discriminative training consistently enhances overall system performance with relative improvements ranging from 11.26%-28.68%. A further extended evaluation using the TIMIT (CORPUS1) and actual noisy aircraft communications data (CORPUS2) shows measurable improvement over the traditional MAP based scheme using the likelihood ratio test (MAP-LRT), with average EERs of 9%-23% for TIMIT and 13%-32% for noisy aircraft communications. The results confirm that an effective in-set/out-of-set speaker recognition system can be formulated using discriminative training for rapid tagging of input speakers from limited training and test data sizesKeywords
This publication has 24 references indexed in Scilit:
- Voice authentication speaks to the marketplaceComputer, 2004
- Minimum verification error training for topic verification2003
- Efficient text-independent speaker verification with structural gaussian mixture models and neural networkIEEE Transactions on Speech and Audio Processing, 2003
- Noise-robust open-set speaker recognition using noise-dependent Gaussian mixture classifier2002
- A Bayesian approach to the verification problem: applications to speaker verificationIEEE Transactions on Speech and Audio Processing, 2001
- Transcript-free search of audio archives for the national gallery of the spoken word2001
- Minimum classification error rate methods for speech recognitionIEEE Transactions on Speech and Audio Processing, 1997
- Text-independent speaker identificationIEEE Signal Processing Magazine, 1994
- Discriminative learning for minimum error classification (pattern recognition)IEEE Transactions on Signal Processing, 1992
- Cepstral analysis technique for automatic speaker verificationIEEE Transactions on Acoustics, Speech, and Signal Processing, 1981