AUT System for SITW Speaker Recognition Challenge

This document intends to present AUT speaker recognition system submitted to SITW (Speakers in the Wild) speaker recognition challenge. This challenge aims to provide real world data across a wide range of acoustic and environmental conditions in the context of automatic speaker recognition so as to facilitate the development of new algorithms. The presented system is based on the state-of-the-art i-vector/PLDA and source normalization techniques. The system has been developed on publically available databases and evaluated on the data provided by SITW challenge. Taking advantage of the challenge development data, our experiments indicate that source normalization can help speaker recognition system to better adapt to the evaluation condition. Post evaluation analysis is conducted on the conditions of SITW database.

[1]  David A. van Leeuwen,et al.  An Introduction to Application-Independent Evaluation of Speaker Recognition Systems , 2007, Speaker Classification.

[2]  David A. van Leeuwen,et al.  Gender-independent speaker recognition using source normalisation , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[3]  David A. van Leeuwen,et al.  Source-Normalized LDA for Robust Speaker Recognition Using i-Vectors From Multiple Speech Sources , 2012, IEEE Transactions on Audio, Speech, and Language Processing.

[4]  Aaron Lawson,et al.  The Speakers in the Wild (SITW) Speaker Recognition Database , 2016, INTERSPEECH.

[5]  Florin Curelaru,et al.  Front-End Factor Analysis For Speaker Verification , 2018, 2018 International Conference on Communications (COMM).

[6]  James H. Elder,et al.  Probabilistic Linear Discriminant Analysis for Inferences About Identity , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[7]  Daniel Garcia-Romero,et al.  Analysis of i-vector Length Normalization in Speaker Recognition Systems , 2011, INTERSPEECH.

[8]  Daniel Povey,et al.  The Kaldi Speech Recognition Toolkit , 2011 .

[9]  W. Marsden.  I and J , 2012 .

[10]  Yun Lei,et al.  A novel scheme for speaker recognition using a phonetically-aware deep neural network , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[11]  M. Graciarena,et al.  THE SPEAKERS IN THE WILD SPEAKER RECOGNITION CHALLENGE PLAN , 2016 .

[12]  Patrick Kenny,et al.  Bayesian Speaker Verification with Heavy-Tailed Priors , 2010, Odyssey.

[13]  Andreas Stolcke,et al.  Within-class covariance normalization for SVM-based speaker recognition , 2006, INTERSPEECH.

[14]  David A. van Leeuwen,et al.  Source normalization for language-independent speaker recognition using i-vectors , 2012, Odyssey.

[15]  Yu Zhang,et al.  Extracting deep neural network bottleneck features using low-rank matrix factorization , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[16]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .