To find clues to terrorists in its terabytes of speech, text, and image data, the NSA uses AI-enhanced link analysis of associated people, places, things and events.

It also relies on decomposing an audio signal to find qualities useful to pattern analysis, using acoustic engineering, behavioral psychology and computational linguistics, as well as clues to deceptive intent in the words and paralinguistic features of a conversation, such as pitch, tone, cadence and latency.