Conference item icon

Conference item

Audio retrieval with natural language queries

Abstract:
We consider the task of retrieving audio using free-form natural language queries. To study this problem, which has received limited attention in the existing literature, we introduce challenging new benchmarks for text-based audio retrieval using text annotations sourced from the AudioCaps and Clotho datasets. We then employ these benchmarks to establish baselines for cross-modal audio retrieval, where we demonstrate the benefits of pre-training on diverse audio tasks. We hope that our benchmarks will inspire further research into cross-modal text-based audio retrieval with free-form text queries.
Publication status:
Published
Peer review status:
Peer reviewed

Actions

Access Document

Files:
Publisher copy:
10.21437/Interspeech.2021-2227

Authors

More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
ORCID:
0000-0002-2478-2102
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author


Publisher:
International Speech Communication Association
Host title:
Proceedings of Interspeech 2021
Pages:
2411-2415
Publication date:
2021-08-30
Acceptance date:
2020-07-24
Event title:
Interspeech 2021
Event location:
Brno, Czechia
Event website:
https://www.interspeech2021.org/
Event start date:
2021-08-30
Event end date:
2021-09-03
DOI:
EISSN:
2308-457X
ISSN:
1990-9772
ISBN:
9781713836902


Language:
English
Keywords:
Pubs id:
1241851
Local pid:
pubs:1241851
Deposit date:
2022-06-10
ARK identifier:

Terms of use


Views and Downloads

Views and downloads will return soon






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

TO TOP