# Speaker Clustering

> Source: https://sukruyusufkaya.com/en/glossary/speaker-clustering
> Updated: 2026-05-13T20:59:28.793Z
> Type: glossary
> Category: ses-konusma-audio-ai
**TLDR:** A diarization subtask that groups similar speech segments so they correspond to the same speaker.

<p>Speaker clustering allows diarization systems to move from raw segments toward real speaker identities. Audio embeddings are used to reveal similarity structure and group segments accordingly. If this stage fails, the same person may be split into multiple identities or different people may be merged together. It is one of the central decision points in audio analytics quality.</p>