Presentation
Scaling Qualitative Analysis of Operational Recordings Using AI Transcription and Subject Matter Expert Review
SessionThursday Poster Session
DescriptionField experimentation with emerging technologies often produces large volumes of audio that capture operator feedback, mission discussion, and human-machine interaction, but manual qualitative analysis of these recordings is time intensive and difficult to scale. This work presents an AI-assisted workflow for accelerating qualitative analysis of operational audio using automated transcription and subject matter expert (SME) review. Audio from military field experiments was transcribed with OpenAI Whisper and then reviewed by SMEs to identify themes related to trust, usability, workload, transparency, and human-machine teaming. The workflow was applied in operationally realistic environments characterized by noise, overlapping speakers, and distributed activities. AI transcription reduced the time required to convert recordings into searchable and reviewable text, while SME review preserved contextual accuracy and analytic relevance. The results show that AI can significantly improve the speed and accessibility of qualitative analysis while still relying on expert interpretation for validation and meaning-making. This approach provides a practical and scalable method for extracting actionable insights from operational recordings in support of experimentation and evaluation.
Contributors
Event Type
Poster
TimeThursday, October 22nd5:30pm - 6:30pm PDT
Location