A||GO – web services platform

The advances of Linkmedia in terms of multimedia analysis and indexing lead to the elaboration of multiple tools available as web-services through the A||GO platform. This platform, created in the context of the PlaSciDo Project and co-managed by Linkmedia and SED Inria, is based on a system of Docker containers allowing multiple environments for a stable access to the web-services. Its philosophy is simple:

  1. Choose your algorithm
  2. Upload your data
  3. Retrieve the result

The multimedia services currently available on A||GO are, w.r.t their modality:

  • Audio processing
    • SaMuSa: music/speech segmentation
    • SilAD: silence detection
    • repeated audio motif discovery
    • LORIA STS v1 and v2: two speech transcription systems from LORIA Multispeech
    • SpeaDS: Speaker Diarization System (who speaks when in an audio stream)
  • Text processing
    • NERO: name entity recognition
    • TermEx: keywords/indexing terms detection
    • Otis!: topic segmentation
    • Hi-tost: hierarchical topic structuring
  • Video processing
    • Vidseg: detection of cuts between visual shots
    • HUFA: face detection

The results of these services can be agglomerated and combined through a common json file. Details about technology transfer and licenses are available within the service documentations on A||GO. For more information, please contact us.


Video excerpts with analysis results

Other free softwares


Toolkit dedicated to audio segmentation and classification of audio


Free speech signal processing toolkit which provides runtime
commands implementing standard feature extraction algorithms for speech
related applications and a C library to implement new algorithms and to
use SPro files within your own programs.


Platform for Indexing Multimedia with Python : The aim of this
module is to provide a convenient and high level API to manage common
multimedia indexing tasks.


This software enables to synchronize slides with the corresponding
video recording

Permanent link to this article: