Title | ||
---|---|---|
Compensation of channel effects for support vector machines based speaker verification |
Abstract | ||
---|---|---|
In this paper, we analyze the effect of channel compensation technique on support vector machines (SVM) based speaker verification performance and compare with another well-known speaker modeling algorithm Gaussian Mixture Models with universal background model (GMM-UBM). Experiments conducted on NIST 2002 SRE shows that channel compensation considerable improves the speaker verification accuracy. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/SIU.2012.6204433 | Signal Processing and Communications Applications Conference |
Keywords | Field | DocType |
speaker recognition,support vector machines,NIST 2002 SRE,channel compensation technique,channel effects generation,speaker modeling algorithm Gaussian Mixture Models,support vector machines based speaker verification,universal background model | Kernel (linear algebra),Speaker verification,Pattern recognition,Computer science,Support vector machine,Communication channel,Speech recognition,NIST,Speaker recognition,Artificial intelligence,Mixture model | Conference |
ISBN | Citations | PageRank |
978-1-4673-0054-4 | 0 | 0.34 |
References | Authors | |
0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Cemal Hanilçi | 1 | 171 | 11.23 |
Figen Ertas | 2 | 0 | 0.34 |