Work

pyannote.audio speaker diarization pipeline at VoxSRC 2023

Year: 2023

Type: report

Abstract: This technical report describes the submission of team pyannote to the VoxSRC 2023 speaker diarization challenge. It relies on 3 stages: local end-to-end neural speaker segmentation on a few seconds sliding window, neural speaker embedding of each speaker of each window, and agglomerative hierarchical clustering.

Source: HAL

Authors: Baroudi, Séverin, Bredin, Hervé, Plaquet, Alexis, Pellegrini, Thomas

Institutions: Centre National de la Recherche Scientifique, Institut de Recherche en Informatique de Toulouse, Université Toulouse III - Paul Sabatier

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Grand Équipement National De Calcul Intensif

OpenAlex ID: W4414761032

Cites: 4

Cited by: 7

Related to: 10