eduzhai > Applied Sciences > Engineering >

FEARLESS STEPS Challenge (FS-2) Supervised Learning with Massive Naturalistic Apollo Data

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 5 pages

Abstract: The Fearless Steps Initiative by UTDallas-CRSS led to the digitization,recovery, and diarization of 19,000 hours of original analog audio data, aswell as the development of algorithms to extract meaningful information fromthis multi-channel naturalistic data resource. The 2020 FEARLESS STEPS (FS-2)Challenge is the second annual challenge held for the Speech and LanguageTechnology community to motivate supervised learning algorithm development formulti-party and multi-stream naturalistic audio. In this paper, we present anoverview of the challenge sub-tasks, data, performance metrics, and lessonslearned from Phase-2 of the Fearless Steps Challenge (FS-2). We presentadvancements made in FS-2 through extensive community outreach and feedback. Wedescribe innovations in the challenge corpus development, and present revisedbaseline results. We finally discuss the challenge outcome and general trendsin system development across both phases (Phase FS-1 Unsupervised, and PhaseFS-2 Supervised) of the challenge, and its continuation into multi-channelchallenge tasks for the upcoming Fearless Steps Challenge Phase-3.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×