Why architecture matters here
Diarization fails on overlap + unknown speaker count. Architecture matters because embed + cluster + fusion compose.
Advertisement
The architecture: every piece explained
The top strip is preprocess. Audio input. VAD. Segments. Speaker embed.
The middle row is grouping. Cluster. Change point. Overlap detection. Labels.
The lower rows are ops. ASR fusion. Metrics. Ops — segment size + threshold + rediarize.
Advertisement
End-to-end flow
End-to-end: audio in. VAD segments speech. 1s windows -> ECAPA embeddings. Spectral clustering with unknown-k. Change-point smooths labels. ASR aligned per segment. Output SPK-01 utterance start-end + text.