Since its introduction in 2019, the whole end-to-end neural diarization
(EEND) line of work has been addressing speaker diarization as a frame-wise
multi-label classification problem with permutation-invariant training. Despite
EEND showing great promise, a few recent works took a step back and studied the
possible combination of (local) supervised EEND diarization with (global)
unsupervised clustering. Yet, these hybrid contributions did not question the
original multi-label formulation. We propose to switch from multi-label (where
any two speakers can be active at the same time) to powerset multi-class
classification (where dedicated classes are assigned to pairs of overlapping
speakers). Through extensive experiments on 9 different benchmarks, we show
that this formulation leads to significantly better performance (mostly on
overlapping speech) and robustness to domain mismatch, while eliminating the
detection threshold hyperparameter, critical for the multi-label formulation.

本文通过对 9 个不同测评的广泛实验，展示了从多标签分类转换到功集多类分类的形式可以显著提高性能（特别是对于重叠语音）和对领域不匹配的鲁棒性，同时消除多标签分类的检测阈值超参数。