pyannote.audio 2.1 speaker diarization pipeline: principle, benchmark, and recipe - Archive ouverte HAL Access content directly
Conference Papers Year : 2023

pyannote.audio 2.1 speaker diarization pipeline: principle, benchmark, and recipe

Abstract

pyannote.audio is an open-source toolkit written in Python for speaker diarization. Version 2.1 introduces a major overhaul of pyannote.audio default speaker diarization pipeline, made of three main stages: speaker segmentation applied to a short sliding window, neural speaker embedding of each (local) speakers, and (global) agglomerative clustering. One of the main objectives of the toolkit is to democratize speaker diarization. Therefore, on top of a pretrained speaker diarization pipeline that gives good results out of the box, we also provide a recipe that practitioners can follow to improve its performance on their own (manually annotated) dataset. It has been used for various challenges and reached 1st place at Ego4D 2022, 1st place at Albayzin 2022, and 6th place at VoxSRC 2022.
Fichier principal
Vignette du fichier
bredin23_interspeech.pdf (427.08 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Licence : Copyright

Dates and versions

hal-04247212 , version 1 (18-10-2023)

Identifiers

Cite

Hervé Bredin. pyannote.audio 2.1 speaker diarization pipeline: principle, benchmark, and recipe. 24th INTERSPEECH Conference (INTERSPEECH 2023), Aug 2023, Dublin, Ireland. pp.1983-1987, ⟨10.21437/Interspeech.2023-105⟩. ⟨hal-04247212⟩
249 View
433 Download

Altmetric

Share

Gmail Facebook X LinkedIn More