Saved in:
Bibliographic Details
Main Authors: Haji-Ali, Moayed, Menapace, Willi, Siarohin, Aliaksandr, Balakrishnan, Guha, Ordonez, Vicente
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.19388
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909580799246336
author Haji-Ali, Moayed
Menapace, Willi
Siarohin, Aliaksandr
Balakrishnan, Guha
Ordonez, Vicente
author_facet Haji-Ali, Moayed
Menapace, Willi
Siarohin, Aliaksandr
Balakrishnan, Guha
Ordonez, Vicente
contents The scalability of ambient sound generators is hindered by data scarcity, insufficient caption quality, and limited scalability in model architecture. This work addresses these challenges by advancing both data and model scaling. First, we propose an efficient and scalable dataset collection pipeline tailored for ambient audio generation, resulting in AutoReCap-XL, the largest ambient audio-text dataset with over 47 million clips. To provide high-quality textual annotations, we propose AutoCap, a high-quality automatic audio captioning model. By adopting a Q-Former module and leveraging audio metadata, AutoCap substantially enhances caption quality, reaching a CIDEr score of $83.2$, a $3.2\%$ improvement over previous captioning models. Finally, we propose GenAu, a scalable transformer-based audio generation architecture that we scale up to 1.25B parameters. We demonstrate its benefits from data scaling with synthetic captions as well as model size scaling. When compared to baseline audio generators trained at similar size and data scale, GenAu obtains significant improvements of $4.7\%$ in FAD score, $11.1\%$ in IS, and $13.5\%$ in CLAP score. Our code, model checkpoints, and dataset are publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2406_19388
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Taming Data and Transformers for Audio Generation
Haji-Ali, Moayed
Menapace, Willi
Siarohin, Aliaksandr
Balakrishnan, Guha
Ordonez, Vicente
Sound
Computation and Language
Computer Vision and Pattern Recognition
Multimedia
Audio and Speech Processing
The scalability of ambient sound generators is hindered by data scarcity, insufficient caption quality, and limited scalability in model architecture. This work addresses these challenges by advancing both data and model scaling. First, we propose an efficient and scalable dataset collection pipeline tailored for ambient audio generation, resulting in AutoReCap-XL, the largest ambient audio-text dataset with over 47 million clips. To provide high-quality textual annotations, we propose AutoCap, a high-quality automatic audio captioning model. By adopting a Q-Former module and leveraging audio metadata, AutoCap substantially enhances caption quality, reaching a CIDEr score of $83.2$, a $3.2\%$ improvement over previous captioning models. Finally, we propose GenAu, a scalable transformer-based audio generation architecture that we scale up to 1.25B parameters. We demonstrate its benefits from data scaling with synthetic captions as well as model size scaling. When compared to baseline audio generators trained at similar size and data scale, GenAu obtains significant improvements of $4.7\%$ in FAD score, $11.1\%$ in IS, and $13.5\%$ in CLAP score. Our code, model checkpoints, and dataset are publicly available.
title Taming Data and Transformers for Audio Generation
topic Sound
Computation and Language
Computer Vision and Pattern Recognition
Multimedia
Audio and Speech Processing
url https://arxiv.org/abs/2406.19388