MSR Identity Toolbox v1.0: A MATLAB Toolbox for Speaker Recognition Research
Citations
177 citations
Cites methods from "MSR Identity Toolbox v1.0: A MATLAB..."
...The system was implemented using the Microsoft Research (MSR) Identity Toolbox [32]....
[...]
140 citations
Cites methods from "MSR Identity Toolbox v1.0: A MATLAB..."
...The MSR Identity Toolbox [25] implementation of the EM GMM training and scoring was used in this research....
[...]
104 citations
Cites methods from "MSR Identity Toolbox v1.0: A MATLAB..."
...2) iVector-PLDA [20] Based Speaker Verification Experiments: To obtain a second baseline performance on the experiments laid out in Tables I, II, III and IV, we perform iVector-PLDA based speaker recognition experiments using the implementation in the MSR identity toolkit [45]....
[...]
...implementation of xVector algorithm was used together with the gaussian PLDA implementation given in the MSR identity toolkit [45] for performing the xVector-PLDA based speaker recognition experiments....
[...]
97 citations
Cites methods from "MSR Identity Toolbox v1.0: A MATLAB..."
...We used three WSJ databases (WSJ0, WSJ1, and WSJCAM) and the Resource Management database (RM1) for training the UBM, eigenspaces, and LDA....
[...]
79 citations
Cites methods from "MSR Identity Toolbox v1.0: A MATLAB..."
...The MSR-Identity toolkit is adopted for the back-end implementation [20]....
[...]
References
10,526 citations
4,673 citations
Additional excerpts
...0: A MATLAB Toolbox for Speaker...
[...]
4,384 citations
"MSR Identity Toolbox v1.0: A MATLAB..." refers methods in this paper
...The dimensionality of the i-vectors are normally reduced through linear discriminant analysis (with Fisher criterion [9]) to annihilate the non-speaker related directions (e....
[...]
...• Sufficient statistics computation for observations given the GMM (compute_bw_stats) [4, 12] • Total variability subspace learning using EM (train_tv_space) [4, 12, 13] • i-vector extraction (extract_ivector) [4, 12, 13] • Linear discriminant analysis (lda) [9] • i-vector length normalization, centering, whitening, and Gaussian probabilistic LDA using EM (gplda-em) [10, 11, 14] • PLDA-based verification trial scoring (score_gplda_trials) [11, 14]...
[...]
3,526 citations
Additional excerpts
...0: A MATLAB Toolbox for Speaker...
[...]
1,099 citations