VESTA - Collaborative multimedia content annotation platform


VESTA is a timeline based annotation platform of multimedia content. It offers an integrated set of innovative computer tools for analyzing and annotating audio and video recordings. These tools allows to significantly accelerate, and in some cases, automate the analysis and annotation of your recordings.

As a web-based collaborative platform, your analysis and annotations can be shared among other researchers, thus increasing cooperation and opening the door to larger-scale multi-partner studies. VESTA results in considerable gains in productivity by significantly reducing analysis time while improving consistency. 

Services 

 

Speaker segmentation

Partition an audio frame into segments according to the identity of the person speaking. This service provides facilities to determine at which times each person is speaking and the gender of each speaker.

Speech-to-text

Transcribe the speech of an audio frame. A domain specific vocabulary can be provided to improve the results.

 
Text-audio matching

Provide correspondence between a given text and an audio frame. This service returns the begin and end positions of each segment found in the two mediums.

Video shot transition detection

Find the temporal positions of the visual transitions between the shots present in a video.

 
Face pose analysis

Identifies the face poses in a video and their orientation (pose in front view, profile or other).

 

How it works

  • Invite researchers and set their access rights.
  • Create studies and upload files.
  • Let our tools annotate your files automatically.
  • Use our graphical tool to build your schemes.
  • Move, merge, split, add, and update annotations.
  • Give other teams access to your work and export it.

 

 Discover and try VESTA here!

 

Read the white paper

 

Reasearch platforms

Created as part of CANARIE-funded projects, the research platforms developed by CRIM are available on the CANARIE's Research Software Portal, which gives access to a range of platforms and software services to researchers in order to accelerate discovery. 

 Discover also PACTE: a collaborative electronic text annotation platform

 

Teams

Recent news

  • Découvrez le CRIM
    13/02/2020

    Acteur clé en TI au Québec ; un lien entre les mondes universitaire et industriel, qui développe, adapte et rend accessibles les technologies et les connaissances, pour répondre aux besoins des organisations.

    +

Upcoming event

  • Seminar R&D : Automated speech-to-text transcription of Indigenous Languages
    28 February 2020 11:00
    CRIM (405, avenue Ogilvy, bureau 101, Montréal)
    A conference of Gilles Boulianne and Vishwa Gupta, Senior Researchers in Automatic Speech Processing, CRIM.
    +
  • Le 4 mars, participez au Webinaire sur le DATALAB pour découvrir comment cette approche progressive peut vous aider… https://t.co/zJmrfNB84I
  • CANARIE RT @CANARIE_Inc: VESTA recueille les données des systèmes d'apprentissage en ligne quand les élèves lisent l'écran, sont distraits ou pense…

Recent Publications

  • Validating BGP Update Using Blockchain-Based Infrastructure

    +
  • Efficient Inference of Optimal Decision Trees

    +