Abstract | ||
---|---|---|
Gaussian mixture models (GMM) have become one of the standard acoustic approaches for language identification. Furthermore, the GMM-SVM is proven to work well by introducing the discriminative method into the GMM-based acoustic systems. In these systems, the intersession variability within language has become an important adverse factor that degrades the system performance. To tackle this problem, we propose a subspace analysis method, termed as Intra-language Difference Subspace Estimation (IDSE), under the GMM-SVM framework. In IDSE method, the difference vector is modeled with three components: Extra-language difference, Intra-language difference and noise difference. Then the Intra-language and noise difference are effectively estimated and eliminated from the difference vector. The experiments on NIST 07 evaluation tasks show effectiveness of the proposed method. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ICME.2009.5202567 | ICME |
Keywords | Field | DocType |
automatic language identification method,discriminative method,idse method,extra-language difference,gmm-svm framework,noise difference,intra-language difference subspace estimation,difference vector,subspace analysis method,intra-language difference,gaussian mixture models,natural language processing,kernel,principal component analysis,system performance,language identification,support vector machines,nist,speech recognition,gaussian processes,gaussian mixture model,mathematical model | Kernel (linear algebra),Subspace topology,Pattern recognition,Computer science,Support vector machine,Speech recognition,NIST,Gaussian process,Artificial intelligence,Language identification,Discriminative model,Mixture model | Conference |
ISSN | Citations | PageRank |
1945-7871 | 1 | 0.35 |
References | Authors | |
9 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yan Song | 1 | 734 | 51.98 |
Li-Rong Dai | 2 | 1070 | 117.92 |
Ren-Hua Wang | 3 | 344 | 41.36 |