State-of-the-Art Performance in Text-Independent Speaker Verification Through Open-Source Software

Fauve, Benoit; Matrouf, Driss; Scheffer, Nicolas; Bonastre, J.-F.; Mason, John S.

doi:10.1109/tasl.2007.902877

Cited by 65 publications

(42 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It turns out that, in the case of a diagonal factor analysis model, using speaker-dependent GMM's does indeed produce better results. For example, on the English language trials in the core condition, a diagonal model with 100 channel factors produces an EER of 2.8% for male speakers, which is similar to the results presented in [30], [5], [31] (but not as good as the result in the first line of Table V).…”

Section: G Note On Baum-welch Statisticssupporting

confidence: 75%

“…The results we have obtained using speaker factors are clearly much better than those obtained using d alone, but the reader may have noticed that the figures presented in the fourth rows of Tables I and II are not quite as good as the best results that have been reported with comparable standalone GMM/UBM systems as in [30], [5], [31]. These systems are comparable because they use relevance MAP for speaker enrollment and channel factors to compensate for intersession variability.…”

Section: G Note On Baum-welch Statisticsmentioning

confidence: 65%

See 1 more Smart Citation

A Study of Interspeaker Variability in Speaker Verification

Kenny

Ouellet

Dehak

et al. 2008

IEEE Trans. Audio Speech Lang. Process.

529

358

View full text Add to dashboard Cite

Abstract-We propose a new approach to the problem of estimating the hyperparameters which define the inter-speaker variability model in joint factor analysis. We tested the proposed estimation technique on the NIST 2006 speaker recognition evaluation data and obtained 10-15% reductions in error rates on the core condition and the extended data condition (as measured both by equal error rates and the NIST detection cost function). We show that when a large joint factor analysis model is trained in this way and tested on the core condition, the extended data condition and the cross-channel condition, it is capable of performing at least as well as fusions of multiple systems of other types. (The comparisons are based on the best results on these tasks that have been reported in the literature.) In the case of the cross-channel condition, a factor analysis model with 300 speaker factors and 200 channel factors can achieve equal error rates of less than 3.0%. This is a substantial improvement over the best results that have previously been reported on this task.

show abstract

Section: G Note On Baum-welch Statisticssupporting

confidence: 75%

Section: G Note On Baum-welch Statisticsmentioning

confidence: 65%

A Study of Interspeaker Variability in Speaker Verification

Kenny

Ouellet

Dehak

et al. 2008

IEEE Trans. Audio Speech Lang. Process.

529

358

View full text Add to dashboard Cite

show abstract

“…They are all based on the LIA-SpkDet toolkit [24] and the ALIZE library [25] and are directly derived from the work in [26]. In all cases the speech signal is divided into frames of 20ms with a frame overlap of 10ms.…”

Section: Asv Systemsmentioning

confidence: 99%

“…The fourth system is almost identical to the third but is enhanced with nuisance attribute projection [29] to attenuate intersession (interchannel) variability, with NAP matrices of rank 40. The fifth approach is a GSL system with FA supervectors (GSL-FA) [26].…”

Section: Asv Systemsmentioning

confidence: 99%

Spoofing countermeasures to protect automatic speaker verification from voice conversion

Alegre

Amehraye

Evans

2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

This paper presents a new countermeasure for the protection of automatic speaker verification systems from spoofed, converted voice signals. The new countermeasure exploits the common shift applied to the spectral slope of consecutive speech frames involved in the mapping of a spoofer's voice signal towards a statistical model of a given target. While the countermeasure exploits prior knowledge of the attack in an admittedly unrealistic sense, it is shown to detect almost all spoofed signals which otherwise provoke significant increases in false acceptance. The work also discusses the need for formal evaluations to develop new countermeasures which are less reliant on prior knowledge.

show abstract

“…For this purposes, the concept of Supervector is introduced, and which is usually referred to mapping many smalldimensional vectors into higher-dimensional vectors (for instance, by stacking the mean vectors of adapted GMM) to feed a SVM classifier (Kinnunen and Li, 2009). Additionally, and for improving even further performance of the GMM-SVM based schema, some developments have been done to address the effects linked to the differences between recording sessions due to transmission channel mismatch, additive noise, linguistic content, and speaker variability (Fauve et al, 2007). For instance the Nuisance Attribute Projection (NAP) (Solomonoff and Campbell, 2007) removes nuisance attribute-related dimensions in the supervector expansion space via projections, aiming to compensate channel and speaker mismatches.…”

Section: Introductionmentioning

confidence: 99%

GMM-based Classifiers for the Automatic Detection of Obstructive Sleep Apnea

García

Blanco-Murillo²,

Godino-Llorente

et al. 2013

Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing

View full text Add to dashboard Cite

Abstract:The aim of automatic pathological voice detection systems is to serve as tools, to medical specialists, for a more objective, less invasive and improved diagnosis of diseases. In this respect, the gold standard for those systern^ include the usage of a^optimized representation of the spectral envelope, either based on cepstral coefficients from the mel-scaled Fourier spectral envelope (Mel-Frequency Cepstral Coefficients) or from an all-pole estimation (Linear Prediction Coding Cepstral Coefficients) for characterization, and Gaussian Mixture Models for posterior classification. However, the study of recently proposed GMM-based classifiers as well as Nuisance mitigation techniques, such as those employed in speaker recognition, has not been widely considered in pathology detection labours. The present work aims at testing whether or not the employmenl|of such speaker recognition tools might contribute to improve system performance in pathology detection systems, specifically in the automatic detection of Obstructive Sleep Apnea. The testing procedure employs^arj^Ob3tructivo Sloop Apnoa database^ in conjunction with GMM-based classifiers looking for a better performance. The results show that an improved performance might be obtained by using such approach.

show abstract

State-of-the-Art Performance in Text-Independent Speaker Verification Through Open-Source Software

Cited by 65 publications

References 16 publications

A Study of Interspeaker Variability in Speaker Verification

A Study of Interspeaker Variability in Speaker Verification

Spoofing countermeasures to protect automatic speaker verification from voice conversion

GMM-based Classifiers for the Automatic Detection of Obstructive Sleep Apnea

Contact Info

Product

Resources

About