I4U submission to NIST SRE 2012: A large-scale collaborative effort for noise-robust speaker verification

R. Saeidi, K. A. Lee, T. Kinnunen, T. Hasan, B. Fauve, P. M. Bousquet, E. Khoury, P. L. Sordo Martinez, J. M.K. Kua, C. H. You, H. Sun, A. Larcher, P. Rajan, V. Hautamäki, C. Hanilci, B. Braithwaite, R. Gonzales-Hautamäki, S. O. Sadjadi, G. Liu, H. BorilN. Shokouhi, D. Matrouf, L. El Shafey, P. Mowlaee, J. Epps, T. Thiruvaran, D. A. Van Leeuwen, B. Ma, H. Li, J. H.L. Hansen, J. F. Bonastre, S. Marcel, J. Mason, E. Ambikairajah

Research output: Journal article publicationConference articleAcademic researchpeer-review

71 Citations (Scopus)

Abstract

I4U is a joint entry of nine research Institutes and Universities across 4 continents to NIST SRE 2012. It started with a brief discussion during the Odyssey 2012 workshop in Singapore. An online discussion group was soon set up, providing a discussion platform for different issues surrounding NIST SRE'12. Noisy test segments, uneven multi-session training, variable enrollment duration, and the issue of open-set identification were actively discussed leading to various solutions integrated to the I4U submission. The joint submission and several of its 17 subsystems were among top-performing systems. We summarize the lessons learnt from this large-scale effort.

Original languageEnglish
Pages (from-to)1986-1990
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Publication statusPublished - Aug 2013
Externally publishedYes
Event14th Annual Conference of the International Speech Communication Association, INTERSPEECH 2013 - Lyon, France
Duration: 25 Aug 201329 Aug 2013

Keywords

  • I4U
  • Ivector
  • NIST SRE 2012
  • Speaker verification

ASJC Scopus subject areas

  • Modelling and Simulation
  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software

Fingerprint

Dive into the research topics of 'I4U submission to NIST SRE 2012: A large-scale collaborative effort for noise-robust speaker verification'. Together they form a unique fingerprint.

Cite this