Fearless Steps Challenge: Phase III
For questions about the challenge (i.e., evaluation plan, data, software), please contact: [email protected]
For questions about the website (i.e., registration, submission), please contact: [email protected]
For the Fearless Steps Challenge discussion please visit our Google Group. https://groups.google.com/a/list.nist.gov/forum/#!forum/fsc
Overview
The Fearless Steps Initiative by UTDallas-CRSS led to the digitization, recovery, and diarization of 19,000 hours of original analog audio data from the NASA Apollo-11 Mission, as well as the development of algorithms to extract meaningful information from this multichannel naturalistic data resource. To motivate a stream-lined and collaborative effort from the speech and language community, UTDallas-CRSS has hosted a series of progressively complex tasks to promote advanced research on naturalistic “Big Data” corpora. This began with Fearless Steps Challenge: Phase I that focused on unsupervised/semi-supervised speech and language solutions for single-channel data with low resource availability and followed with Fearless Steps Challenge: Phase II which focused on developing supervised learning strategies for the 100 hour Challenge Corpus.For hosting the Fearless Steps Challenge: Phase III (FSC P3), UTDallas-CRSS is partnering with OpenSAT. The FSC P3 focuses on the development of single-channel supervised learning strategies with an aim to test system generalizability to varying channel and mission data . All FSC P3 evaluation activities (registration, system output submission, scoring, and leaderboard display) will be conducted through web-interfaces hosted by OpenSAT.
For general instructions and help with the OpenSAT web platform, please visit Help.
To register for this challenge, please follow the instructions at: https://fearless-steps.github.io/ChallengePhase3/registration.
To prepare and submit system outputs for this challenge, please follow the instructions at: https://fearless-steps.github.io/ChallengePhase3/submission