Speaker Diarization

Speaker Diarization automatically partitions an audio stream, leveraging AI to identify and label who spoke when in multi-speaker recordings.

This AI-driven process segments an audio file, performing two core functions: Speaker Detection (identifying the total number of unique voices) and Speaker Attribution (assigning each speech segment to a specific label, e.g., Speaker 1, Speaker 2). The system analyzes voice characteristics (pitch, tone) to create speaker embeddings, clustering them for high-accuracy labeling. This capability is critical for enhancing Automatic Speech Recognition (ASR) readability, transforming raw meeting transcripts and call center analytics into actionable, speaker-attributed data.

https://www.assemblyai.com/blog/what-is-speaker-diarization/