Support Vector Gmms for Speaker Verification

Dehak, Najim; Chollet, G.

doi:10.1109/odyssey.2006.248131

Cited by 23 publications

(14 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the universal background model (UBM) is included as a part in most speaker recognition systems, it provides a natural way to create supervectors [38,52,132]. This leads to hybrid classifier where the generative GMM-UBM model is used for creating "feature vectors" for the discriminative SVM.…”

Section: Gaussian Supervector Svmmentioning

confidence: 99%

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

Kinnunen¹,

Li²

2010

Speech Communication

1,239

706

View full text Add to dashboard Cite

This paper gives an overview of automatic speaker recognition technology, with an emphasis on text-independent recognition. Speaker recognition has been studied actively for several decades. We give an overview of both the classical and the state-of-the-art methods. We start with the fundamentals of automatic speaker recognition, concerning feature extraction and speaker modeling. We elaborate advanced computational techniques to address robustness and session variability. The recent progress from vectors towards supervectors opens up a new area of exploration and represents a technology trend. We also provide an overview of this recent development and discuss the evaluation methodology of speaker recognition systems. We conclude the paper with discussion on future directions.

show abstract

Section: Gaussian Supervector Svmmentioning

confidence: 99%

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

Kinnunen¹,

Li²

2010

Speech Communication

1,239

706

View full text Add to dashboard Cite

show abstract

“…where E w ij T n o could be obtained by concatenating the results from (22) and (23). The second moment E w ij w ij T n o is computed for each individual session and speaker as follows:…”

Section: M-step: Model Estimationmentioning

confidence: 99%

“…Support vector machine (SVM) is acknowledged as one of the pre-eminent discriminative approaches [16][17][18], and it has been successfully combined with GMM, such as the GMM-SVM [8,9,[19][20][21]. Nevertheless, approaches based on GMM-SVM are unable to cope well with the channel effects [22,23]. To compensate for the channel effects, it was shown using the joint factor analysis (JFA) technique that the speaker and channel variability can be confined as two disjoint subspaces in the parameter spaces of GMM [12,24].…”

Section: Introductionmentioning

confidence: 99%

PLDA in the i-supervector space for text-independent speaker verification

Jiang

Lee

Wang

2014

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

In this paper, we advocate the use of the uncompressed form of i-vector and depend on subspace modeling using probabilistic linear discriminant analysis (PLDA) in handling the speaker and session (or channel) variability. An i-vector is a low-dimensional vector containing both speaker and channel information acquired from a speech segment. When PLDA is used on an i-vector, dimension reduction is performed twice: first in the i-vector extraction process and second in the PLDA model. Keeping the full dimensionality of the i-vector in the i-supervector space for PLDA modeling and scoring would avoid unnecessary loss of information. We refer to the uncompressed i-vector as the i-supervector. The drawback in using the i-supervector with PLDA is the inversion of large matrices in the estimation of the full posterior distribution, which we show can be solved rather efficiently by portioning large matrices into smaller blocks. We also introduce the Gaussianized rank-norm, as an alternative to whitening, for feature normalization prior to PLDA modeling. We found that the i-supervector performs better during normalization. A better performance is obtained by combining the i-supervector and i-vector at the score level. Furthermore, we also analyze the computational complexity of the i-supervector system, compared with that of the i-vector, at four different stages of loading matrix estimation, posterior extraction, PLDA modeling, and PLDA scoring.

show abstract

“…Since the universal background model (UBM) is included as a part in most speaker recognition systems, it provides a natural way to create supervectors [12]. This leads to hybrid classifier where the generative GMM-UBM model is used for creating "feature vector" for the discriminative SVM.…”

Section: Gmm Supervectormentioning

confidence: 99%

Factor Analysis of Neighborhood-Preserving Embedding for Speaker Verification

Chen

Yang

Zhao

2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn this letter, we adopt a new factor analysis of neighborhood-preserving embedding (NPE) for speaker verification. NPE aims at preserving the local neighborhood structure on the data and defines a low-dimensional speaker space called neighborhood-preserving embedding space. We compare the proposed method with the state-of-the-art total variability approach on the telephone-telephone core condition of the NIST 2008 Speaker Recognition Evaluation (SRE) dataset. The experimental results indicate that the proposed NPE method outperforms the total variability approach, providing up to 24% relative improvement.

show abstract

Support Vector Gmms for Speaker Verification

Cited by 23 publications

References 17 publications

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

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

PLDA in the i-supervector space for text-independent speaker verification

Factor Analysis of Neighborhood-Preserving Embedding for Speaker Verification

Contact Info

Product

Resources

About