Conference item icon

Conference item

VoxCeleb2: Deep speaker recognition

Abstract:

The objective of this paper is speaker recognition under noisy and unconstrained conditions.


We make two key contributions. First, we introduce a very large-scale audio-visual speaker recognition dataset collected from open-source media. Using a fully automated pipeline, we curate VoxCeleb2 which contains over a million utterances from over 6,000 speakers. This is several times larger than any publicly available speaker recognition dataset.


Second, we develop and compare Convolutional Neural Network (CNN) models and training strategies that can effectively recognise identities from voice under various conditions. The models trained on the VoxCeleb2 dataset surpass the performance of previous works on a benchmark dataset by a significant margin.

Publication status:
Published
Peer review status:
Peer reviewed

Actions

Access Document

Files:
Publisher copy:
10.21437/Interspeech.2018-1929

Authors

More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
Brasenose College
Role:
Author
ORCID:
0000-0002-8945-8573


Publisher:
International Speech Communication Association
Host title:
Interspeech 2018
Journal:
Interspeech 2018 More from this journal
Publication date:
2018-09-06
Acceptance date:
2018-06-03
DOI:
ISSN:
1990-9772


Keywords:
Pubs id:
pubs:944820
UUID:
uuid:08ab75c5-aa1c-49fc-b36a-1280c6a309c4
Local pid:
pubs:944820
Source identifiers:
944820
Deposit date:
2018-11-21
ARK identifier:

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP