pyannote.audio 2.1 speaker diarization pipeline: principle, benchmark, and recipe - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

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

Résumé

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
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Licence : Copyright (Tous droits réservés)

Dates et versions

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

Identifiants

Citer

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⟩
424 Consultations
1018 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More