Abstract | ||
---|---|---|
In this paper we introduce the angle of models Mahalanobis distance as the test algorithm in the text- independent speaker verification system. In test process, the test speech is adapted to a new model instead of calculating the log-likelihood ratio scores, then the Mahalanobis distances among the UBM model, the speaker model and the test speech model are calculated. These three models distances form a triangle. The angle of the triangle can be treated as the test scores. When we employ the proposed algorithm in GMM_UBM system, the recognition rate can be almost identical with the traditional log-likelihood ratio scores, while the computation load can be dramatically cut down. That is very helpful to the real-time application of the speaker recognition or verification. Further more, when we fuse angle scores with the log-likelihood ratio scores, the EER of the speaker verification can be reduced by 12~15% in 2002 NIST evaluation corpus. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1109/FSKD.2007.174 | FSKD (4) |
Keywords | Field | DocType |
speaker model,speaker verification,test process,new model,ubm model,models distance,test algorithm,test speech model,independent speaker verification system,log-likelihood ratio score,test speech,test score,log likelihood ratio,mahalanobis distance,gaussian processes,speaker recognition | Speaker verification,Test algorithm,Computer science,Mahalanobis distance,Speaker recognition,Artificial intelligence,Gaussian process,Fuse (electrical),Computation,Pattern recognition,Speech recognition,NIST,Machine learning | Conference |
ISBN | Citations | PageRank |
0-7695-2874-0 | 0 | 0.34 |
References | Authors | |
7 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wu Guo | 1 | 13 | 6.79 |
Pan Lei | 2 | 5 | 0.83 |
Ren-Hua Wang | 3 | 344 | 41.36 |
Li-Rong Dai | 4 | 1070 | 117.92 |