Joint frame and Gaussian selection for text independent speaker verification

Saeidi, Rahim; Kinnunen, Tomi; Mohammadi, Hamid Reza; Rodman, Robert D.; Fränti, Pasi

doi:10.1109/icassp.2010.5495576

Cited by 5 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Results obtained with search width of 512 are better than those obtained with the sorted function in [7]. More recently, another extension of the method explained in [3] is proposed by Saeidi et al in [8], using a two-dimensional indexation, allowing simultaneous selection of Gaussian and frames. The evaluation was developed using several values of a control parameter to specify the neighborhood of the optimization (2%, 3%, 5%, 10%, 15% and 20%) obtaining speed-up ratios of 157:1, 85:1, 37:1, 11:1, 5:1 and 3:1, respectively.…”

Section: Introductionmentioning

confidence: 99%

Gaussian Selection for Speaker Recognition Using Cumulative Vectors

Diaz

Lara

Sierra

2012

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

Abstract. Speaker recognition systems frequently use GMM -MAP method for modeling speakers. This method represents a speaker using a Gaussian mixture. However in this mixture not all the Gaussian components are truly representative of the speaker. In order to remove the model redundancy, this work proposes a Gaussian selection method to achieve a new GMM model only with the more representative Gaussian components. Speaker verification experiments applying the proposal show a similar performance to baseline; however the speaker models have a reduction of 80 % regarding the speaker model used for baseline. The application of this Gaussian selection method in real or embedded speaker verification systems could be very useful for reducing computational and memory cost.

show abstract

Section: Introductionmentioning

confidence: 99%

Gaussian Selection for Speaker Recognition Using Cumulative Vectors

Diaz

Lara

Sierra

2012

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

show abstract

“…More recently, another extension of the method explained in [13] is proposed by Saeidi et al in [15], using a two-dimensional indexation, allowing simultaneous selection of Gaussian and frames. The evaluation was developed using several values of a control parameter to specify the neighborhood of the optimization (2%, 3%, 5%, 10%, 15% and 20%) obtaining speed-up ratios of 157:1, 85:1, 37:1, 11:1, 5:1 and 3:1, respectively.…”

Section: Introductionmentioning

confidence: 99%

A Gaussian Selection Method for Speaker Verification with Short Utterances

Diaz¹,

Sierra²,

Lara³

2014

CyS

View full text Add to dashboard Cite

Speaker recognition systems frequently use GMM-MAP method for modeling speakers. This method represents the speaker using a Gaussian mixture. However, in this mixture not all Gaussian components are truly representative of the speaker. In order to remove the model redundancy, this work proposes a Gaussian selection method to achieve a new GMM model only with the more representative Gaussian components. The results of speaker verification experiments applying the proposal show a similar performance to the baseline; however, the speaker models used have a reduction of 80% compared to the speaker model used as the baseline. Our proposal was also applied to speaker recognition system with short test signals of 15, 5 and 3 seconds obtaining an improvement in EER of 0.43%, 2.64% and 1.60%, respectively, compared to the baseline. The application of this method in real or embedded speaker verification systems could be very useful for reducing computational and memory cost.

show abstract

“…One of these methods is the GMM hashing ( Leon, 2015), where top scoring mixtures for a feature vector can be predicted by using a GMM that is smaller than the UBM. Another method is hierarchically clustering the UBM mixtures (Xiang, Berger, 2003;Saeidi et al, 2010). Some of the other methods are speaker clustering at feature level (Xiong et al, 2006), and speaker clustering at model level (Beigi et al, 1999; De Leon, Apsingekar, 2007; Apsingekar, De Leon, 2009).…”

Section: Introductionmentioning

confidence: 99%

Speaker Model Clustering to Construct Background Models for Speaker Verification

DİŞKEN

Tüfekçi

Çevik

2017

Archives of Acoustics

View full text Add to dashboard Cite

Conventional speaker recognition systems use the Universal Background Model (UBM) as an imposter for all speakers. In this paper, speaker models are clustered to obtain better imposter model representations for speaker verification purpose. First, a UBM is trained, and speaker models are adapted from the UBM. Then, the k-means algorithm with the Euclidean distance measure is applied to the speaker models. The speakers are divided into two, three, four, and five clusters. The resulting cluster centers are used as background models of their respective speakers. Experiments showed that the proposed method consistently produced lower Equal Error Rates (EER) than the conventional UBM approach for 3, 10, and 30 seconds long test utterances, and also for channel mismatch conditions. The proposed method is also compared with the i-vector approach. The three-cluster model achieved the best performance with a 12.4% relative EER reduction in average, compared to the i-vector method. Statistical significance of the results are also given.

show abstract

Joint frame and Gaussian selection for text independent speaker verification

Cited by 5 publications

References 12 publications

Gaussian Selection for Speaker Recognition Using Cumulative Vectors

Gaussian Selection for Speaker Recognition Using Cumulative Vectors

A Gaussian Selection Method for Speaker Verification with Short Utterances

Speaker Model Clustering to Construct Background Models for Speaker Verification

Contact Info

Product

Resources

About