APOLLO Fearless Steps: A Community Resource for Massive Naturalistic Communications

TIMELINE:Challenge Start Date (Train/Dev Data Release): February 1^st, 2022

Evaluation Data Release: March 7^th, 2022

Evaluation Portal Open (Data Release): March 10^th, 2022

INTERSPEECH-2022 Paper submission deadline: March 28^th, 2022

Open Challenge Duration: from February 1^st, 2022, to September 15^th, 2022

Challenge Tasks in Phase-4 (FS#4):

1. Speech Activity Detection (SAD)

2. Speaker Recognition:

2a. Track 1: Speaker Identification (SID)

2b. Track 2: Speaker Verification (SV)

3. Speaker Diarization (SD):

3a. Track 1: Diarization using reference SAD

3b. Track 2: Diarization using system SAD

4. Automatic Speech Recognition (ASR):

4a. Track 1: ASR using reference Diarization

4b. Track 2: Continuous stream ASR

5. Topic Identification:

5a. Track 1: Topic Detection

5b. Track 2: Topic Segmentation

For Challenge Registration, please contact: FearlessSteps@utdallas.edu

Website Link: https://fearless-steps.github.io/ChallengePhase4/

Background

We are pleased to announce the APOLLO Fearless Steps Special Sessionto be held at INTERSPEECH-2022. The focus of this Special Session is to provide a forum for researchers working on the massive naturalistic audio collection stemming from the NASA Apollo Missions. UTDallas-CRSS under NSF support has led the Fearless Steps Initiative, a continued effort spanning eight years has resulted in the digitization, and recovery of over 50,000 hours of original analog audio data, as well as the development of algorithms to extract meaningful information from this naturalistic data resource, including an initial release of pipeline diarization meta-data for all 30 channels of APOLLO-11 and APOLLO-13 Missions. More than 500 sites worldwide have accessed the initial data. A current NSF Community Resource project is continuing this effort to recover the remaining Apollo missions (A7-A17; estimated to be 150,000hrs of data) in addition to motivating collaborative speech and language technology research through the Fearless Steps Challenge series.

We invite all researchers to submit papers to this special session which use Fearless Steps speech data as a data set for their research. In addition, this special session is also connected with the next phase of the Fearless Steps Challenge (FS-4) to be held from Feb. 1 to Sept. 15, 2022. Any team worldwide can participate and submit their output scoring summaries with a leaderboard being updated regularly (see Fearless Steps FS-4 Challenge logistics below). If your organization, university, team wishes to submit a specific solution on FS-4 for Interspeech-2022, we welcome you to do this as well and submit your paper to this Special Session. A major goal of this Special Session is to allow for researchers to discuss and provide feedback on how they have used this public data resource, and how ongoing efforts can make this data more useful for the speech technology/psychology-team research/history-STEM education communities.

Organizers

John H.L. Hansen (john.hansen@utdallas.edu)

Christopher Ceiri (ccieri@ldc.upenn.edu)

Jim Horan (jim.horan@nist.gov)

Aditya Joglekar (aditya.joglekar@utdallas.edu)

Midia Yousefi (midia.yousefi@utdallas.edu)

Meena Chandra Shekar (meena.chandrashekar@utdallas.edu)