Analysis of the BUT Diarization System for Voxconverse Challenge

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F21%3APU142913" target="_blank" >RIV/00216305:26230/21:PU142913 - isvavai.cz</a>

Result on the web

<a href="https://ieeexplore.ieee.org/document/9414315" target="_blank" >https://ieeexplore.ieee.org/document/9414315</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICASSP39728.2021.9414315" target="_blank" >10.1109/ICASSP39728.2021.9414315</a>

Result language

angličtina

Original language name

Analysis of the BUT Diarization System for Voxconverse Challenge

Original language description

This paper describes the system developed by the BUT team for the fourth track of the VoxCeleb Speaker Recognition Challenge, focusing on diarization on the VoxConverse dataset. The system consists of signal pre-processing, voice activity detection, speaker embedding extraction, an initial agglomerative hierarchical clustering followed by diarization using a Bayesian hidden Markov model, a reclustering step based on per-speaker global embeddings and overlapped speech detection and handling. We provide comparisons for each of the steps and share the implementation of the most relevant modules of our system. Our system scored second in the challenge in terms of the primary metric (diarization error rate) and first according to the secondary metric (Jaccard error rate).

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2021

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

ISBN

978-1-7281-7605-5

ISSN

—

e-ISSN

—

Number of pages

5

Pages from-to

5819-5823

Publisher name

IEEE Signal Processing Society

Place of publication

Toronto, Ontario

Event location

Toronto, Canada

Event date

Jun 6, 2021

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000704288406018