Abstract | ||
---|---|---|
In this paper we propose an speaker verification approach by applying low-rank recovery approach under total variability space, which is trained by a modified Gaussian Mixture Modeling (MGMM) with the observation confidence. In this model, we construct UBM mean supervector by MGMM in order to train total variability matrix and obtain i-vectors. Besides, the low-rank recovery method is exploited to model i-vectors under the total variability space. Experiment results on utterances from Korean movie ("You came from the stars") show that our proposed approach can significantly enhance the performance of speaker verification and outperform the baseline GMM_UBM, GMM-supervector in noisy environments |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/ICITCS.2015.7293016 | 2015 5th International Conference on IT Convergence and Security (ICITCS) |
Keywords | Field | DocType |
speaker verification,low-rank recovery approach,total variability space,modified Gaussian mixture modeling,MGMM,observation confidence,UBM mean supervector,i-vectors | Speech enhancement,Speaker verification,Mixture modeling,Pattern recognition,Noise measurement,Computer science,Matrix (mathematics),Signal-to-noise ratio,Speech recognition,Gaussian,Artificial intelligence,Aerospace electronics | Conference |
ISSN | Citations | PageRank |
2473-0122 | 2 | 0.36 |
References | Authors | |
8 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tan Dat Trinh | 1 | 5 | 1.14 |
Jin Young Kim | 2 | 497 | 81.76 |
Hyoung-Gook Kim | 3 | 163 | 22.36 |
Kyongrok Lee | 4 | 2 | 0.70 |