IBERSPEECH 2020

Valladolid, November 18-20, 2020

Albayzin-RTVE 2020 Multimodal diarization and identification Challenge

The multimodal diarization and identification evaluation consists of segmenting broadcast audiovisual documents according to a closed set of different speakers and faces and linking those segments which originate from the same speaker and face. For this evaluation, a list of characters to recognize will be given. The rest of characters on the audiovisual document will be discarted for the evaluation purposes. System outputs must give for each segment who is speaking and who is/are in the image from the list of characters. For each character, a set of face pictures and short audiovisual document will be given.

This year an optional scene diarization is proposed. The scene diarization consists of segmenting broadcast audiovisual documents according to a closed set of descriptors. The descriptors are: day, night, urban, rural, summer, winter, indoor, outdoor and multiscreen.

The calendar for the Albayzín Multimodal Diarization and Identification evaluation is:
  • March 23th, 2020: Registration opens
  • March 23th, 2020: Release of the training and development data
  • June 1st, 2020 September 7th, 2020: Registration deadline. Release of the evaluation data
  • June 30th, 2020 October 9th, 2020: Submission deadline
  • July 15th, 2020 October 30th, 2020: Results distribution to the participants
  • September 13, 2020 December 23th, 2020: Paper submission deadline
  • November 18-20, 2020 March, 2021: Iberspeech 2020 conference in Valladolid
More details in the evaluation plan