Results 1 - 10
of
21
Speaker verification using Adapted Gaussian mixture models
- Digital Signal Processing
, 2000
"... In this paper we describe 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). The system is built around the likelihood ratio test for verification, using simple but ef ..."
Abstract
-
Cited by 1010 (42 self)
- Add to MetaCart
(Show Context)
In this paper we describe 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). The system is built around the likelihood ratio test for verification, using simple but effective GMMs for likelihood functions, a universal background model (UBM) for alternative speaker representation, and a form of Bayesian adaptation to derive speaker models from the UBM. The development and use of a handset detector and score normalization to greatly improve verification performance is also described and discussed. Finally, representative performance benchmarks and system behavior experiments on NIST SRE corpora are presented. © 2000 Academic Press Key Words: speaker recognition; Gaussian mixture models; likelihood ratio detector; universal background model; handset normalization; NIST evaluation. 1.
A Tutorial on Text-Independent Speaker Verification
- EURASIP JOURNAL ON APPLIED SIGNAL PROCESSING 2004:4, 430–451
, 2004
"... This paper presents an overview of a state-of-the-art text-independent speaker verification system. First, an introduction proposes a modular scheme of the training and test phases of a speaker verification system. Then, the most commonly speech parameterization used in speaker verification, namely, ..."
Abstract
-
Cited by 138 (13 self)
- Add to MetaCart
This paper presents an overview of a state-of-the-art text-independent speaker verification system. First, an introduction proposes a modular scheme of the training and test phases of a speaker verification system. Then, the most commonly speech parameterization used in speaker verification, namely, cepstral analysis, is detailed. Gaussian mixture modeling, which is the speaker modeling technique used in most systems, is then explained. A few speaker modeling alternatives, namely, neural networks and support vector machines, are mentioned. Normalization of scores is then explained, as this is a very important step to deal with real-world data. The evaluation of a speaker verification system is then detailed, and the detection error trade-off (DET) curve is explained. Several extensions of speaker verification are then enumerated, including speaker tracking and segmentation by speakers. Then, some applications of speaker verification are proposed, including on-site applications, remote applications, applications relative to structuring audio information, and games. Issues concerning the forensic area are then recalled, as we believe it is very important to inform people about the actual performance and limitations of speaker verification systems. This paper concludes by giving a
Generalized Linear Discriminant Sequence Kernels For Speaker Recognition
, 2002
"... Support Vector Machines have recently shown dramatic performance gains in many application areas. We show that the same gains can be realized in the area of speaker recognition via sequence kernels. A sequence kernel provides a numerical comparison of speech utterances as entire sequences rather tha ..."
Abstract
-
Cited by 95 (23 self)
- Add to MetaCart
Support Vector Machines have recently shown dramatic performance gains in many application areas. We show that the same gains can be realized in the area of speaker recognition via sequence kernels. A sequence kernel provides a numerical comparison of speech utterances as entire sequences rather than a probability at the frame level. We introduce a novel sequence kernel derived from generalized linear discriminants. The kernel has several advantages. First, the kernel uses an explicit expansion into "feature space"--this property allows all of the support vectors to be collapsed into a single vector creating a small speaker model. Second, the kernel retains the computational advantage of generalized linear discriminants trained using mean-squared error training. Finally, the kernel shows dramatic reductions in equal error rates over standard mean-squared error training in matched and mismatched conditions on a NIST speaker recognition task.
Gaussian Selection Applied to Text-Independent Speaker Verification
- In Proc. Speaker Odyssey 2001
, 2001
"... Fast speaker verification systems can be realised by reducing the computation associated with searching of mixture components within the statistical model such as a Gaussian mixture model, GMM. Several improvements regarding computational efficiency have already been proposed ..."
Abstract
-
Cited by 16 (1 self)
- Add to MetaCart
Fast speaker verification systems can be realised by reducing the computation associated with searching of mixture components within the statistical model such as a Gaussian mixture model, GMM. Several improvements regarding computational efficiency have already been proposed
Speaker recognition with polynomial classifiers
- IEEE Transactions on Speech and Audio Processing
"... ..."
An Overview Of The Cave Project - Research Activities In Speaker Verification
, 1998
"... This paper describes the technology used and the results achieved by WP4. It complements a former paper, published during the course of the project [1] ..."
Abstract
-
Cited by 13 (1 self)
- Add to MetaCart
This paper describes the technology used and the results achieved by WP4. It complements a former paper, published during the course of the project [1]
A Sequence Kernel and its Application to Speaker Recognition
- in Neural Information Processing Systems 14
, 2001
"... A novel approach for comparing sequences of observations using an explicit-expansion kernel is demonstrated. The kernel is derived using the assumption of the independence of the sequence of observations and a mean-squared error training criterion. The use of an explicit expansion kernel reduces ..."
Abstract
-
Cited by 9 (0 self)
- Add to MetaCart
(Show Context)
A novel approach for comparing sequences of observations using an explicit-expansion kernel is demonstrated. The kernel is derived using the assumption of the independence of the sequence of observations and a mean-squared error training criterion. The use of an explicit expansion kernel reduces classifier model size and computation dramatically, resulting in model sizes and computation one-hundred times smaller in our application. The explicit expansion also preserves the computational advantages of an earlier architecture based on mean-squared error training.
Video Genre Verification using both Acoustic and Visual Modes
, 2002
"... This paper reports on the verification of the video genre: sport, cartoon, news, commercial and music. Results for the two modes, acoustic and visual, and for combined modes show an average equal error rate (ERR) of 16%, 15% and 10%. respectively. These reflect verification accuracy and as such are ..."
Abstract
-
Cited by 8 (0 self)
- Add to MetaCart
(Show Context)
This paper reports on the verification of the video genre: sport, cartoon, news, commercial and music. Results for the two modes, acoustic and visual, and for combined modes show an average equal error rate (ERR) of 16%, 15% and 10%. respectively. These reflect verification accuracy and as such are believed to be the first of their kind; previously published work has focused on closed set identifaction, assuming the video is known to belong to one of a fixed set.
Classifying Accelerometer Data via Hidden Markov Models to authenticate People by the Way they Walk
- In 45th IEEE International Carnahan Conference on Security Technology
, 2011
"... Abstract – Promising results have been obtained when using Hidden Markov Models for accelerometer-based biometric gait recognition. So far, the used testing data contains only walking straight on a flat floor, which is not a realistic scenario. This paper shows the results when using a more realisti ..."
Abstract
-
Cited by 2 (1 self)
- Add to MetaCart
(Show Context)
Abstract – Promising results have been obtained when using Hidden Markov Models for accelerometer-based biometric gait recognition. So far, the used testing data contains only walking straight on a flat floor, which is not a realistic scenario. This paper shows the results when using a more realistic data set containing walking around corners, upstairs and downstairs etc. It is analyzed to which extent the biometric performance is degraded when this more demanding data set is used. To show practical results the cross-day performance is analyzed and compared with the same-day results. Error rates will be given depending on the amount of training data and after a voting scheme is applied. We obtain an Equal Error Rate (EER) of 6.15 % which is less than a third of the EER obtained when applying a cycle extraction method to the same data set. Index Terms — biometric gait recognition, accelerometers,
Automatic Speaker Recognition: Current Approaches and Future Trends •1
"... In this paper we provide a brief overview of the area of speaker recognition, defining terminology, discussing applications, describing underlying techniques and providing some indications of performance. Following this overview we compare speaker verification to other biometrics and discuss some of ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
In this paper we provide a brief overview of the area of speaker recognition, defining terminology, discussing applications, describing underlying techniques and providing some indications of performance. Following this overview we compare speaker verification to other biometrics and discuss some of the strengths and weaknesses of speaker verification technology. Finally we outline some potential future trends in research and development. 1.
