Meeting Intelligence Glossary
Clear definitions of the concepts behind modern meeting analysis.
Speaker Diarization
Speaker diarization is the automatic process of partitioning an audio recording into segments labeled by speaker identity. It answers the question "who spoke when?" without requiring prior knowledge of the speakers' voices. In meeting intelligence, diarization transforms a monolithic audio stream into a structured, speaker-attributed transcript that enables per-speaker analysis.
Meeting Intelligence
Meeting intelligence refers to the use of AI to extract structured, actionable information from meeting recordings. It encompasses transcription, speaker identification, topic extraction, summary generation, action item detection, and — in more advanced systems — behavioral analysis and conversational dynamics. The term distinguishes tools that merely transcribe from those that analyze and synthesize meeting content into usable insights.
Conversational Dynamics
Conversational dynamics are the patterns of interaction between participants in a conversation. They include turn-taking behavior (who speaks when and for how long), interruption patterns, engagement signals (elaboration vs. minimal responses), pace changes, topic avoidance, and the implicit power structure that emerges from how people communicate. Unlike content (what was said), dynamics capture the social and behavioral layer of conversation.
Behavioral Meeting Analysis
Behavioral meeting analysis is the systematic examination of how meeting participants communicate, as distinct from what they communicate. It encompasses observable behavioral signals — speech pace, hesitation patterns, turn-taking behavior, interruption frequency, response elaboration, engagement changes, and interpersonal dynamics. It produces structured observations about individual and group communication patterns rather than content summaries or action items.
Raw Audio Cues
Raw Audio Cues are auraScribe's foundational behavioral data layer. They are an exhaustive, chronological log of observable behavioral signals extracted during a dedicated audio analysis pass (Pass 2 of the 3-pass pipeline). Each cue is a timestamped observation about a specific speaker's communication behavior — pace changes, hesitation patterns, interruptions, engagement shifts, turn-taking dynamics, micro-signals, and interpersonal interactions. They are the raw material from which behavioral summaries, per-speaker remarks, and buyer intent signals are synthesized.
Stop exporting transcripts. Start delivering.
Try auraScribe free for 14 days. You talk — auraScribe takes it from there.
Try auraScribe