Conference item icon

Conference item

A sound approach: using large language models to generate audio descriptions for egocentric text-audio retrieval

Abstract:
Video databases from the internet are a valuable source of text-audio retrieval datasets. However, given that sound and vision streams represent different "views" of the data, treating visual descriptions as audio descriptions is far from optimal. Even if audio class labels are present, they commonly are not very detailed, making them unsuited for text-audio retrieval. To exploit relevant audio information from video-text datasets, we introduce a methodology for generating audio-centric descriptions using Large Language Models (LLMs). In this work, we consider the egocentric video setting and propose three new text-audio retrieval benchmarks based on the EpicMIR and EgoMCQ tasks, and on the EpicSounds dataset. Our approach for obtaining audio-centric descriptions gives significantly higher zero-shot performance than using the original visual-centric descriptions. Furthermore, we show that using the same prompts, we can successfully employ LLMs to improve the retrieval on EpicSounds, compared to using the original audio class labels of the dataset. Finally, we confirm that LLMs can be used to determine the difficulty of identifying the action associated with a sound.
Publication status:
Published
Peer review status:
Peer reviewed

Actions

Access Document

Files:
Publisher copy:
10.1109/icassp48485.2024.10448486

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
Oxford college:
Brasenose College
Role:
Author
ORCID:
0000-0002-8945-8573


Publisher:
IEEE
Host title:
Proceedings of the 49th IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP 2024)
Pages:
7300-7304
Publication date:
2024-04-14
Acceptance date:
2024-04-14
Event title:
49th IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP 2024)
Event location:
Seoul, South Korea
Event website:
https://2024.ieeeicassp.org/
Event start date:
2024-04-14
Event end date:
2024-04-19
DOI:
EISSN:
2379-190X
ISSN:
1520-6149
EISBN:
979-8-3503-4485-1
ISBN:
979-8-3503-4486-8


Language:
English
Keywords:
Pubs id:
1987486
Local pid:
pubs:1987486
Deposit date:
2024-06-12
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