The First DIHARD Speech Diarization Challenge

New upload

The First DIHARD Speech Diarization Challenge

Speaker diarization is the task of determining "who spoke when" in a multispeaker environment and is an essential component of many speech recognition tasks processing large volumes of data (e.g., police body cam recordings, large corpora of meetings). While the state-of-the-art diarization methods work remarkably well on the cases that have been considered thus far (e.g., CallHome or two-person callcenter communications), this success does not transfer to more challenging corpora such as "speech in the wild" (YouTube videos, recordings from wearables, etc). DIHARD is the first of a series of challenges aiming to break this last barrier.


Curated by:
dihardchallenge
Curation policy:

Available from http://coml.lscp.ens.fr/dihard/submission.html

Created:
January 16, 2018
Harvesting API:
OAI-PMH Interface

Want your upload to appear in this community?

  • Click the button above to upload straight to this community.
  • The community curator is notified, and will either accept or reject your upload (see community curation policy above).
  • If your upload is rejected by the curator, it will still be available on Zenodo, just not in this community.