English

Streaming Sortformer: Speaker Cache-Based Online Speaker Diarization with Arrival-Time Ordering

Audio and Speech Processing 2025-07-25 v1 Sound

Abstract

This paper presents a streaming extension for the Sortformer speaker diarization framework, whose key property is the arrival-time ordering of output speakers. The proposed approach employs an Arrival-Order Speaker Cache (AOSC) to store frame-level acoustic embeddings of previously observed speakers. Unlike conventional speaker-tracing buffers, AOSC orders embeddings by speaker index corresponding to their arrival time order, and is dynamically updated by selecting frames with the highest scores based on the model's past predictions. Notably, the number of stored embeddings per speaker is determined dynamically by the update mechanism, ensuring efficient cache utilization and precise speaker tracking. Experiments on benchmark datasets confirm the effectiveness and flexibility of our approach, even in low-latency setups. These results establish Streaming Sortformer as a robust solution for real-time multi-speaker tracking and a foundation for streaming multi-talker speech processing.

Keywords

Cite

@article{arxiv.2507.18446,
  title  = {Streaming Sortformer: Speaker Cache-Based Online Speaker Diarization with Arrival-Time Ordering},
  author = {Ivan Medennikov and Taejin Park and Weiqing Wang and He Huang and Kunal Dhawan and Jinhan Wang and Jagadeesh Balam and Boris Ginsburg},
  journal= {arXiv preprint arXiv:2507.18446},
  year   = {2025}
}

Comments

Accepted to Interspeech 2025

R2 v1 2026-07-01T04:17:06.580Z