Abstract | ||
---|---|---|
This paper proposes a classification scheme that com- bines statistical models and support vector machines. It exploits the fact (observed in (1)) that GMM and SVM classifiers with roughly the same level of performance produce uncorrelated errors. We describe a novel scheme which employs an SVM classifier as an "advisor" to the GMM classifier in uncertain cases. The utility of the combined generative/discriminative approach is demon- strated on standard text-independent speaker verification and speaker identification tasks in matched and mismatched training and test conditions. Results indicate significant improvements in performance without much computa- tional overhead. |
Year | Venue | Keywords |
---|---|---|
2001 | INTERSPEECH | statistical model,support vector machine |
Field | DocType | Citations |
Overhead (computing),Speaker identification,Pattern recognition,Computer science,Classification scheme,Support vector machine,Uncorrelated,Speech recognition,Statistical model,Artificial intelligence,Classifier (linguistics),Discriminative model | Conference | 6 |
PageRank | References | Authors |
0.92 | 8 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shai Fine | 1 | 1112 | 107.56 |
Jiri Navratil | 2 | 314 | 31.36 |
ji r navr atil | 3 | 6 | 0.92 |
Ramesh A. Gopinath | 4 | 323 | 42.58 |