跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 9 天前AI 評分47

eDIAR:透過 e-means 實現免訓練的開放説話者串流分段,適用於長會議和大型檔案庫

eDIAR: Training-Free Open-Speaker Streaming Diarization for Long Meetings and Large Archives via e-means

AI 導讀

eDIAR 以 e-means 在所有説話者槽位用盡後再聚類嵌入向量,無需重新訓練即可解除串流説話者分段的固定人數上限。在長達一小時的會議中,它比 Streaming Sortformer 更準確,而且每次更新的成本不隨會議長度增加;e-means 亦以快數倍的速度達到 Lloyd's k-means 的聚類品質。

正文

Published on Nov 13

Authors:

,

,

,

Abstract

A streaming speaker-diarization method removes the fixed speaker-slot limit by clustering speaker embeddings within slots after all slots are used, allowing unlimited speakers and efficient large-scale linking.

Meetings last up to an hour, and nobody knows in advance how many people will speak. Neural diarizers with a fixed number of output slots, such as Streaming Sortformer and Nemotron-3, are accurate and run online, but they cannot name more speakers than they have slots. We remove this limit without retraining. The slot head keeps deciding who is active and when speech overlaps, and speaker embeddings are clustered inside a single slot, with the official e-means algorithm, only after every slot has been used. In the streaming system, re-clustering is confined to a bounded window, labels are revised for a few seconds, and identities are anchored to the slots of the head. The resulting system has no limit on the number of speakers and stays accurate when speakers outnumber the slots, where fixed-slot models break down. On meetings that grow to an hour it stays far more accurate than Streaming Sortformer, which accumulates errors, and its cost per update does not grow with the meeting. The same recipe turns the four-slot Streaming Sortformer into an open-speaker system. Across recordings, e-means makes it affordable to link the speakers of a large archive frame by frame, a task that arises when conversational corpora are prepared, and it reaches the clustering quality of Lloyd's k-means several times faster. The method needs little tuning, and e-means runs with its default recipe from a few hundred to more than a million embeddings.

View arXiv page View PDF Project page Add to collection

Models citing this paper 1

Kyudan/eDIAR

Updated about 1 hour ago

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.18529 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.18529 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co