Voice biometrics

Our expertise in voice biometrics, an area of research aimed at identifying or authenticating a person's identity through its voice, is one of the most advanced in the world.

In the course of our 2005, 2006, 2008 and 2010 participations in the National Institute of Standards and Technology (NIST) Speaker Recognition Evaluation campaigns, our results ranked among the best in the word. The impact of our work on the community has been felt since our second year of participation by changes in the testing paradigm and the adoption of factorial analysis, i-vectors and probabilistic linear discriminant analysis by the most competitive sites. Each year since 2006, CRIM claims the first place in several of the evaluation conditions of NIST SRE.

Related technologies: Speaker verification, speaker segmentation, password authentication, voice activity detection

Video - How to identify a person by speech (French)

Teams

Releases

Publications

Recent news

  • The Joy of Reading, by De Marque
    18/04/2018

    Before the web existed, we worked a lot in schools and were motivated to offer content in digital form, specifically francophone and Quebecois content, because what existed at the time was mainly in English...

    +

Upcoming event

  • R-D Seminar - Towards coherent, fluent and context-appropriate Natural Language Generation systems
    24 April 2018 11:00
    CRIM (405, avenue Ogilvy, bureau 101, Montréal)
    A presentation by Jad Kabbara, scholarship student within the Speech and Text team at CRIM, and Ph.D. candidate at the School of Computer Science at McGill University.
    +

Recent Publications

  • Towards Automatic Feature Extraction for Activity Recognition from Wearable Sensors: A Deep Learning Approach

    +
  • État des lieux des technologies web

    +