Skip to content
conftrace_
2017 Interspeech INTERSPEECH 2017

The MIT-LL, JHU and LRDE NIST 2016 Speaker Recognition Evaluation System

Abstract

In this paper, the NIST 2016 SRE system that resulted from the collaboration between MIT Lincoln Laboratory and the team at Johns Hopkins University is presented. The submissions for the 2016 evaluation consisted of three fixed condition submissions and a single system open condition submission. The primary submission on the fixed (and core) condition resulted in an actual DCF of .618. Details of the submissions are discussed along with some discussion and observations of the 2016 evaluation campaign.

Authors

Pedro A. Torres-Carrasquillo, Fred Richardson, Shahan Nercessian, Douglas Sturim, William Campbell, Youngjune Gwon, Swaroop Vattam, Najim Dehak, Harish Mallidi, Phani Sankar Nidadavolu, Ruizhi Li, Reda Dehak

Topics

Machine Learning > Core Methods > Classification Machine Learning > Optimization & Theory > Statistical Learning

Keywords

speaker verification speaker recognition detection cost function evaluation system nist sre
Download PDF

More from Interspeech 2017

All Interspeech 2017 papers →
Frame and Segment Level Recurrent Neural Networks for Phone Classification
Deep Learning-Based Telephony Speech Recognition in the Wild
The I4U Mega Fusion and Collaboration for NIST Speaker Recognition Evaluation 2016
Nuance - Politecnico di Torino’s 2016 NIST Speaker Recognition Evaluation System
UTD-CRSS Systems for 2016 NIST Speaker Recognition Evaluation
Analysis and Description of ABC Submission to NIST SRE 2016