Paper Info
Title
Support Vector Machines Versus Fast Scoring In The Low-Dimensional Total Variability Space For Speaker Verification
Abstract
This paper presents a new speaker verification system architecture based on Joint Factor Analysis (JFA) as feature extractor. In this modeling, the JFA is used to define a new low-dimensional space named the total variability factor space. instead of both channel and speaker variability spaces for the classical JFA. The main contribution in this approach, is the use of the cosine kernel in the new total factor space to design two different systems: the first system is Support Vector Machines based, and the second one uses directly this kernel as a decision score. This last scoring method makes the process faster and less computation complex compared to others classical methods. We tested several intersession compensation methods in total factors, and we found that the combination of Linear Discriminate Analysis and Within Class Covariance Normalization achieved the best performance. We achieved a remarkable results using fast scoring method based only on cosine kernel especially for male trials, we yield an EER of 1.12% and MinDCF of 0.0094 on the English trials of the NIST 2008 SRE dataset.
Year
Venue
Keywords
2009
INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5
Total variability space, cosine kernel, fast scoring, support vector machines
Field
DocType
Citations 
Kernel (linear algebra),Trigonometric functions,Normalization (statistics),Pattern recognition,Computer science,Support vector machine,Speech recognition,NIST,Artificial intelligence,Linear discriminant analysis,Covariance,Computation
Conference
131
PageRank 
References 
Authors
9.34
6
6
Search Limit
100131
Name
Order
Citations
PageRank
N. Dehak1126992.64
R. Dehak264435.47
Patrick Kenny32700214.80
Niko Brümmer459544.01
Pierre Ouellet5136579.52
Pierre Dumouchel61759129.78