Title | ||
---|---|---|
Discriminatively Trained Probabilistic Linear Discriminant Analysis For Speaker Verification |
Abstract | ||
---|---|---|
Recently, i-vector extraction and Probabilistic Linear Discriminant Analysis (PLDA) have proven to provide state-of-the-art speaker verification performance. In this paper, the speaker verification score for a pair of i-vectors representing a trial is computed with a functional form derived from the successful PLDA generative model. In our case, however, parameters of this function are estimated based on a discriminative training criterion. We propose to use the objective function to directly address the task in speaker verification: discrimination between same-speaker and different-speaker trials. Compared with a baseline which uses a generatively trained PLDA model, discriminative training provides up to 40% relative improvement on the NIST SRE 2010 evaluation task. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICASSP.2011.5947437 | 2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING |
Keywords | Field | DocType |
Speaker verification, Discriminative training, Probabilistic Linear Discriminant Analysis | Speaker verification,Pattern recognition,Computer science,Support vector machine,Feature extraction,Speech recognition,NIST,Speaker recognition,Artificial intelligence,Probabilistic logic,Discriminative model,Generative model | Conference |
ISSN | Citations | PageRank |
1520-6149 | 59 | 3.16 |
References | Authors | |
9 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lukas Burget | 1 | 126 | 8.38 |
Oldrich Plchot | 2 | 327 | 30.88 |
Sandro Cumani | 3 | 200 | 18.81 |
Ondřej Glembek | 4 | 852 | 64.75 |
Petr Schwarz | 5 | 991 | 69.47 |
Niko Brümmer | 6 | 595 | 44.01 |