Fearless steps, NASA’s first heroes: Conversational speech analysis of the Apollo-11 mission control personnel

Abstract

Between 1963 and 1972, a massive team of dedicated scientists, engineers, and specialists at the NASA Mission Control Center (MCC) worked seamlessly together in a cohesive manner to successfully carry out multiple manned missions to the moon. All communications between personnel were carried out over multiple inter-connected audio channels and recorded on two 30-track analog tapes. Digitization of the entire Apollo-11 mission tapes made possible through the UTDallas-CRSS Fearless Steps (FS) initiative contains the recordings of all the crew members including the three astronauts. With over 600 speakers in constant communication ensuring the astronauts’ safety throughout the mission, the success of the Apollo missions can be attributed largely to the MCC crew members. The focus of this effort is thus, to analyze their high-level group dynamics and intricate communication characteristics and gain insight into the success parameters involved in such large-scale time-critical operations. The 100 hour FS Challenge corpus highlights multiple salient moments like Lift-Off and Lunar-Landing and poses its’ own challenges for core speech tasks. This effort aims at analyzing spontaneous multi-speaker conversations in recordings often degraded by various noise types. Analysis of speech characteristics under varying stress, overlap, and noise conditions are observed to develop novel speech-activity and speaker models. These domain-specific models are leveraged to develop state-of-the-art SLT systems.

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

“…The NASA Apollo Mission Control recordings are rich source of time-critical team based communications. Complex communication characteristics in this corpus can be explored through multiple avenues, and require vast resource utilization [16,17]. outreach and feedback.…”

Speaker Representation Learning Using Global Context Guided Channel and Time-Frequency Transformations

“…Several new temporal pooling methods like attentive pooling [18], Spatial Pyramid Pooling [19] and GhostVLAD [20] were presented to aggregate the variable length input features to a fixed-length utterance level representation. Various noise and language robust speaker recognition models [21,22,23,24], and training paradigms [25,26] have been proposed and significantly improve speaker verification systems' performance. Cai et al [27] introduced a Learnable Dictionary Encoding (LDE) layer to combine frame-level speaker features to an utterancelevel speaker embedding.…”

Data-driven Attention and Data-independent DCT based Global Context Modeling for Text-independent Speaker Recognition

“…Several new temporal pooling methods including attentive pooling [27], [28], Spatial Pyramid Pooling [29], and LDE [30] are able to aggregate variable length input features to a fixed-length utterance level representation. Various noise and language robust speaker recognition models [31], [11], [32], [33], training paradigms [34], [35], and domain adaptation [36], [37] methods have been proposed and significantly improve speaker verification system performance.…”