On the calibration of powerset speaker diarization models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Plaquet, Alexis, Bredin, Hervé
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916409485819904
author Plaquet, Alexis
Bredin, Hervé
author_facet Plaquet, Alexis
Bredin, Hervé
contents 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-the-art on multiple datasets. In this paper, we propose to study the calibration of a powerset speaker diarization model, and explore some of its uses. We study the calibration in-domain, as well as out-of-domain, and explore the data in low-confidence regions. The reliability of model confidence is then tested in practice: we use the confidence of the pretrained model to selectively create training and validation subsets out of unannotated data, and compare this to random selection. We find that top-label confidence can be used to reliably predict high-error regions. Moreover, training on low-confidence regions provides a better calibrated model, and validating on low-confidence regions can be more annotation-efficient than random regions.
format Preprint
id arxiv_https___arxiv_org_abs_2409_15885
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On the calibration of powerset speaker diarization models
Plaquet, Alexis
Bredin, Hervé
Sound
Machine Learning
Audio and Speech Processing
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-the-art on multiple datasets. In this paper, we propose to study the calibration of a powerset speaker diarization model, and explore some of its uses. We study the calibration in-domain, as well as out-of-domain, and explore the data in low-confidence regions. The reliability of model confidence is then tested in practice: we use the confidence of the pretrained model to selectively create training and validation subsets out of unannotated data, and compare this to random selection. We find that top-label confidence can be used to reliably predict high-error regions. Moreover, training on low-confidence regions provides a better calibrated model, and validating on low-confidence regions can be more annotation-efficient than random regions.
title On the calibration of powerset speaker diarization models
topic Sound
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2409.15885