Audio Intelligence with Dr. Andre Martin
"Terabytes of audio, waiting for a pipeline that can make them searchable and analytically useful."
What students do
Over five weeks, students build a working audio intelligence pipeline from scratch, moving through the same pattern that powers serious research on large audio corpora: audio to text, find the construct in the text, analyze the audio around it.
It starts with listening. Students spend time with recorded business communications, developing an ear for what executives communicate beyond the numbers — the hesitations, the emphasis, the moments where language choices reveal something the data alone cannot. From there they build each stage of the pipeline: transcribing audio, applying a dictionary and a language model to find the same constructs and comparing what each misses, mapping findings back to the original audio, and extracting vocal features from the moments that matter.
The final week asks students to tell a story. They build a visualization, identify the most interesting moments in the recording, and present their findings to the cohort. They leave with a working multi-stage pipeline they built and debugged themselves, the experience of connecting a research question to a concrete analytical artifact, and a foundation they can extend independently — into new corpora, new constructs, or new questions of their own.
About the mentor
Dr. Andre Martin is an assistant professor at Notre Dame's Mendoza College of Business whose PhD in marketing opened a different question: what can AI reveal about human behavior, language, and persuasion in real business contexts? This summer students build a working audio intelligence pipeline, transcribing business conversations, detecting constructs in the text, and extracting vocal features from the moments that matter, developing real NLP and signal processing skills on actual data.