Voice-to-text conversion tool for CEDROM-SNi radio monitoring


Context:Strategic intelligence and monitoring activities enable institutions and businesses to better cope with the changes that regularly occur in their business environment. Specialized in the niche of media monitoring, CEDROM-SNi has been working for more than 25 years to interpret and analyze the multitude of data and statements produced by the print media, radio, television and social media. The more difficult treatment of radio content prompted the company to purchase a commercial voice-to-text conversion tool to consolidate its radio monitoring offerings. Achieving mixed results with this technology, the company decided to call on CRIM.

Project CRIM’s  team worked closely with CEDROM-SNi to develop, perfect and deploy a voice-to-text conversion tool for radio content, adapted to CEDROM-SNi’s needs. Thanks to CRIM, CEDROM-SNi is achieving substantial savings by using its custom tool compared to a commercial tool. CRIM is now helping the company rethink its data architecture.

CRIM’s unique role: CRIM distinguished itself from its competitors by offering services adapted to the particular needs of CEDROM-SNi. CRIM researchers adjusted and recalibrated their tool so that it could meet a much higher demand for productivity. The team worked to develop a solution that was an optimal compromise between speed of execution and quality of transcription. CRIM’s experts had also anticipated the organizational changes that necessarily accompany the deployment of any new technology. They took an active part in integrating the tool into the technical and organizational systems of the company.

Teams

Recent news

  • Best wishes for the holidays!
    18/12/2019

    Happy Holidays from all of us at 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.
    +
  • Nous y serons!! https://t.co/CxzO3DDoUy
  • Infolettre de janvier 2020 ????pour avoir les dernières nouvelles du CRIM, ses membres et partenaires.… https://t.co/8sKn8SXVe0

Recent Publications

  • On the use of Fisher Vector Encoding for Voice Spoofing Detection

    +
  • Deep learning speech recognition for low-resource languages

    +