The First DIHARD Speech Diarization Challenge

New upload

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.

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:
Curation policy:

Available from

January 16, 2018
Harvesting API:
OAI-PMH Interface