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

TL;DR

The paper describes the second phase of the FEARLESS STEPS Challenge, focusing on supervised learning with a large, naturalistic multi-channel audio dataset, highlighting advancements, lessons learned, and future directions in speech technology.

Contribution

It introduces the FS-2 challenge, detailing its data, tasks, results, and innovations, advancing supervised learning methods for naturalistic multi-party audio analysis.

Findings

Improved baseline results for multi-stream audio tasks

Insights into system development trends across challenge phases

Enhanced dataset and challenge design for future research

Abstract

The Fearless Steps Initiative by UTDallas-CRSS led to the digitization, recovery, and diarization of 19,000 hours of original analog audio data, as well as the development of algorithms to extract meaningful information from this multi-channel naturalistic data resource. The 2020 FEARLESS STEPS (FS-2) Challenge is the second annual challenge held for the Speech and Language Technology community to motivate supervised learning algorithm development for multi-party and multi-stream naturalistic audio. In this paper, we present an overview of the challenge sub-tasks, data, performance metrics, and lessons learned from Phase-2 of the Fearless Steps Challenge (FS-2). We present advancements made in FS-2 through extensive community outreach and feedback. We describe innovations in the challenge corpus development, and present revised baseline results. We finally discuss the challenge outcome and general trends in system development across both phases (Phase FS-1 Unsupervised, and Phase FS-2 Supervised) of the challenge, and its continuation into multi-channel challenge tasks for the upcoming Fearless Steps Challenge Phase-3.