Over-Tightening-Aware Pseudo-Labeling for Tight-Boundary Speaker Diarization

2026-09-09

AI Summary

本文针对伪标签过紧导致的漏检问题，提出去除停顿填充、引入预热阶段及改进协同训练方法，提高说话人日志边界精度和下游任务性能。

Abstract

Training speaker diarization models on loose labels, such as speech segments with padded boundaries or filled pauses, often results in similarly loose model outputs. To obtain tighter boundaries, pseudo-labeling based on the averaged outputs of causal and anticausal models has been proposed. However, since the pseudo-labels are estimation-based, they can suffer from over-tightening, which increases missed detections that can propagate as unrecoverable errors to downstream tasks. This paper carefully analyzes the causes of over-tightening and proposes three approaches to address them: (i) removing pause filling rather than padding, (ii) introducing a burn-in phase to mitigate missed detections near the beginning of causal and anticausal predictions, and (iii) making pseudo-label-based co-training aware of the non-causal model used for final inference. Experimental results show that the proposed method reduces missed detections caused by over-tightening and improves both diarization accuracy and downstream multi-talker ASR performance.

Problem

• pseudo-labeling
• over-tightening
• speaker diarization

Innovation

• Over-Tightening
• Pseudo-Labeling
• Burn-in Phase
• Missed Detections
• Speaker Diarization