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

  • Une assemblée générale et un cocktail annuel réussis!
    21/06/2018

    L'assemblée générale, présidée par M. Luc Gagnon, chef des technologies chez TELUS Santé et président du CA du CRIM, fut l'occasion de dresser un bilan des résultats dévoilés dans le rapport d'activités 2017-2018.

    +

Upcoming event

  • CVPR 2018
    22 June 2018 0:00
    Salt Lake City, Utah.
    CRIM will participate at this importante Conference on Computer Vision and Pattern Recognition to be held from june 18 to 22, 2018 in Salt Lake City.
    +
  • @cefrio @ENCQOR_Qc Le CRIM sera au rendez-vous!
  • CEFRIO RT @cefrio: Surveillez le fil @ENCQOR_Qc le 22 juin: une belle annonce concernant l’initiative #5G #ENCQOR vous y attends! Rendez-vous dema…

Recent Publications

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

    +
  • État des lieux des technologies web

    +