Megaphone project


Summary: Megaphone was an interactive outdoor installation in Montréal's Quartier des spectacles (QDS), that allowed citizens to speak out publicly on a theme of their choice. Participants saw their words converted into giant visual art projected onto the front of the great UQAM Président-Kennedy building, thanks to Moment Factory imaging and CRIM speech recognition technologies. CRIM participated as a consultant for speech recognition in the project's initial phase, provided its technologies for real-time and offline recognition, and contributed to the integration of its technologies into the system installed at QDS.

Result: The installation final version included a live system, that projected words in real-time on a container located behind the speakers, and an offline system, which produced more accurate results that appeared 20 seconds later onto UQAM's building et were accumulated there as a long term memory of the spoken words. English and French were supported. Hundreds of participants used the installation between September 4 and November 4, 2013.

Partners: Moment Factory, National Film Board of Canada (NFB), Quartier des spectacles Montréal.

NFB video - A few candid moments at Megaphone

Teams

Recent news

  • Retour sur l'AGA 2020
    06/07/2020

    Le CRIM a tenu sa 35e assemblée générale annuelle le 18 juin 2020. Plusieurs membres étaient présents pour souligner une année de croissance importante pour l’organisme.

    +

Upcoming event

  • Gala des Prix Innovation 2020 de l'ADRIQ
    19 November 2020 0:00
    Palais des Congrès de Montréal
    Le Gala Prix Innovation 2020 de l'ADRIQ aura lieu le 19 novembre 2020, au Palais des congrès de Montréal.
    +
  • CSCIENCE IA RT @CSCIENCEIA: Une année marquante pour les membres du Centre de recherche informatique de Montréal (@CRIM_ca). L’organisme termine l’une…
  • PRIMA Québec RT @PRIMAQUEBEC: Bénéficiez d’une grande notoriété auprès de l’écosystème de la recherche et de l’innovation du Québec en appliquant sur le…

Recent Publications

  • On The Performance of Time-Pooling Strategies for End-to-End Spoken Language Identification

    +
  • An ensemble Based Approach for Generalized Detection of Spoofing Attacks to Automatic Speaker Recognizers

    +