Emotion detection system


Summary: The emotion detection project based on person-machine dialogues aimed at facilitating the evaluation of the telephone user support service of Bell. It  can detect the presence of negative emotional states during exchanges between Bell clients and its virtual agent. 

Result: Two detection systems have been developed. The first relates to clientele dissatisfaction and the second relates to  negative emotions that have been expressed. 

Partners: Laboratoires Universitaires Bell.

 

Teams

Recent news

  • CRIM Audio Description Technology: Technoleads takes the reigns
    10/12/2019

    Technoleads Services, Inc., an innovative media services provider, announces that they have completed the process to independently operate the audio description technology developed by CRIM.

    +

Upcoming event

  • Transformation numérique - Secteur public - Événement Les Affaires
    29 January 2020 7:00
    DoubleTree par Hilton, Montréal
    Le CRIM fier partenaire de la 1ère édition sur la Transformation numérique - Secteur public organisée par les Événement Les Affaires, qui se tiendra les 29 janvier 2020 au DoubleTree par Hilton, Montréal.
    +
  • NRC Canada RT @NRC_CNRC: Most audio archives of Indigenous languages have not been indexed for keyword search. We are working with @CRIM_ca @Pirurvik…
  • CNRC RT @CNRC_NRC: Avec @CRIM_ca, @Pirurvik et @CBCNorth, nous cherchons à faciliter la recherche ???? par mot-clé dans les archives audio en #inuk…

Recent Publications

  • Deep learning speech recognition for low-resource languages

    +
  • Forage de données géospatiales, quelques applications

    +