Powerset multi-class cross entropy loss for neural speaker diarization
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.
Code (1)
Tasks
Multi-class ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONspeaker-diarizationSpeaker DiarizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PowerCLIP: Powerset Alignment for Contrastive Pre-Training
Contrastive vision-language pre-training frameworks such as CLIP have demonstrated impressive zero-shot performance across a range of vision-language tasks. Recent studies have shown that aligning individual text tokens …
YNU-HPCC at SemEval-2022 Task 6: Transformer-based Model for Intended Sarcasm Detection in English and Arabic
In this paper, we (a YNU-HPCC team) describe the system we built in the SemEval-2022 competition. As participants in Task 6 (titled “iSarcasmEval: Intended Sarcasm Detection In English and Arabic”), we implement the sent…
Binary ClassificationClassificationSarcasm DetectionSentence+1Powerset Convolutional Neural Networks
We present a novel class of convolutional neural networks (CNNs) for set functions, i.e., data indexed with the powerset of a finite set. The convolutions are derived as linear, shift-equivariant functions for various no…
On the calibration of powerset speaker diarization models
End-to-end neural diarization models have usually relied on a multilabel-classification formulation of the speaker diarization problem. Recently, we proposed a powerset multiclass formulation that has beaten the state-of…
speaker-diarizationSpeaker DiarizationImbalanced Multi-label Classification for Business-related Text with Moderately Large Label Spaces
In this study, we compared the performance of four different methods for multi label text classification using a specific imbalanced business dataset. The four methods we evaluated were fine tuned BERT, Binary Relevance,…
Multi-Label ClassificationMUlTI-LABEL-ClASSIFICATIONMulti Label Text ClassificationMulti-Label Text Classification+2