INTERSPEECH 2009
10th Annual Conference of the International Speech Communication Association

Brighton, United Kingdom
September 6-10, 2009

The MIT Lincoln Laboratory 2008 Speaker Recognition System

D. E. Sturim, W. M. Campbell, Zahi N. Karam, Douglas Reynolds, F. S. Richardson

MIT, USA

In recent years methods for modeling and mitigating variational nuisances have been introduced and refined. A primary emphasis in last years NIST 2008 Speaker Recognition Evaluation (SRE) was to greatly expand the use of auxiliary microphones. This offered the additional channel variations which has been a historical challenge to speaker verification systems. In this paper we present the MIT Lincoln Laboratory Speaker Recognition system applied to the task in the NIST 2008 SRE. Our approach during the evaluation was two-fold: 1) Utilize recent advances in variational nuisance modeling (latent factor analysis and nuisance attribute projection) to allow our spectral speaker verification systems to better compensate for the channel variation introduced, and 2) fuse systems targeting the different linguistic tiers of information, high and low. The performance of the system is presented when applied on a NIST 2008 SRE task. Post evaluation analysis is conducted on the sub-task when interview microphones are present.

Full Paper

Bibliographic reference.  Sturim, D. E. / Campbell, W. M. / Karam, Zahi N. / Reynolds, Douglas / Richardson, F. S. (2009): "The MIT lincoln laboratory 2008 speaker recognition system", In INTERSPEECH-2009, 2359-2362.