Enhancing GMM speaker identification by incorporating SVM speaker verification for intelligent web-based speech applications

Ding, Ing-Jr; Yen, Chih-Ta

doi:10.1007/s11042-013-1587-5

Cited by 16 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Since Bayesian Networks yielded the worst results in the previous study [19], they were subsequently replaced by support vector machines (SVM) with a radial basis function (RBF) kernel. SVMs, originally proposed in [34], have been used with various kernels (e.g., linear, polynomial and radial) for data classification in a wide range of studies, e.g., in food categorization [30], speaker recognition [10,20] or personality traits recognition based on handwriting [16]. The RBF kernel [32] is well-known for its high classification power.…”

Section: Experimental Set-upmentioning

confidence: 99%

Increasing anti-spoofing protection in speaker verification using linear prediction

Janicki

2016

Multimed Tools Appl

View full text Add to dashboard Cite

This article addresses the problem of anti-spoofing protection in an automatic speaker verification (ASV) system. An improved version of a previously proposed spoofing countermeasure is presented. The presented method is based on the analysis of linear prediction error that results from both short-and long-term prediction of the input speech signal. It was observed that non-natural speech signals, i.e., synthetic or converted speech, were predicted in a different way than genuine speech. Therefore, in contrast to the classical linear prediction analysis, where usually only the prediction coefficients are analyzed, in the proposed approach the residual (error) signals were examined. During this analysis, 23 various prediction parameters were extracted, such as the energy of the prediction error, prediction gains and temporal parameters related to the prediction error signals. Various binary classifiers were researched to separate human and spoof classes, however the support vector machines with radial basis function (SVM-RBF) yielded the best results. When tested on the corpora provided for the ASVspoof 2015 Challenge, the proposed countermeasure returned better results than the previous version of the algorithm and, in most of the cases, the baseline spoofing detector based on the local binary patterns (LBP). It is hoped that the proposed method can be part of a generalized spoofing countermeasure helping to increase security of ASV systems.The calculations described in the article were made in the Interdisciplinary Centre for Mathematical and Computational Modelling (ICM) of the University of Warsaw (computational grant No. G46-2).

show abstract

Section: Experimental Set-upmentioning

confidence: 99%

Increasing anti-spoofing protection in speaker verification using linear prediction

Janicki

2016

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…The eighth paper entitled "Enhancing GMM Speaker Identification by Incorporating SVM Speaker Verification for Intelligent Web-Based Speech Applications" by Ing-Jr Ding and Chih-Ta Yen [2] focuses on the promising applications on the feature recognition over voice. Authors propose an EGMM-SVM model, that incorporates the Gaussian mixture method and support vector machine, to make improvement on accuracy of the estimated likelihood scores on existing Gaussian mixture method and quality transmission on support vector machine.…”

Section: Summary Of Accepted Papersmentioning

confidence: 99%

Social Media Services and Technologies Towards Web 3.0

Yen

Zhang

Waluyo

et al. 2015

Multimed Tools Appl

View full text Add to dashboard Cite

“…And the adaptive factor provides the connecting bridge for weights, mean before and after updating the model. It also maintains a balance between the model data [6]. The established process of GMM speaker model is shown in Figure 1.…”

Section: A the Speaker Modelmentioning

confidence: 99%

A speaker recognition algorithm based on factor analysis

Shen

Zhai

Wang

et al. 2014

2014 7th International Congress on Image and Signal Processing

View full text Add to dashboard Cite

Channel interference factor for the identification result is prevalent among the existing speaker recognition algorithms. In order to improve the accuracy of the algorithm, the paper utilizes the technique of latent factor analysis(LFA) to deal with the channel factors in the speaker's Gaussian Mixture Model(GMM). In the endpoint detection phase of speaker recognition, the algorithm introduces the GMM for speech modeling to accurately determine the beginning and ending points of the speech segment, and then establish speaker GMM. The algorithm use factor analysis technique to fit the differences between the speaker characteristics space and the channel space, and removes channel factor in speaker's GMM. And then the algorithm extracts GMM super-vectors as the input of Support Vector Machine(SVM) to obtain recognition results. Experimental results show that the combination of factor analysis and SVM can obtain better recognition rate and ensure the robustness of the recognition algorithm. (Abstract)

show abstract

Enhancing GMM speaker identification by incorporating SVM speaker verification for intelligent web-based speech applications

Cited by 16 publications

References 16 publications

Increasing anti-spoofing protection in speaker verification using linear prediction

Increasing anti-spoofing protection in speaker verification using linear prediction

Social Media Services and Technologies Towards Web 3.0

A speaker recognition algorithm based on factor analysis

Contact Info

Product

Resources

About