Saved in:
Bibliographic Details
Main Author: Chung, HaeChun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.22166
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908733760602112
author Chung, HaeChun
author_facet Chung, HaeChun
contents Text-to-audio (TTA) generation can significantly benefit the media industry by reducing production costs and enhancing work efficiency. However, most current TTA models (primarily diffusion-based) suffer from slow inference speeds and high computational costs. In this paper, we introduce AudioGAN, the first successful Generative Adversarial Networks (GANs)-based TTA framework that generates audio in a single pass, thereby reducing model complexity and inference time. To overcome the inherent difficulties in training GANs, we integrate multiple ,contrastive losses and propose innovative components Single-Double-Triple (SDT) Attention and Time-Frequency Cross-Attention (TF-CA). Extensive experiments on the AudioCaps dataset demonstrate that AudioGAN achieves state-of-the-art performance while using 90% fewer parameters and running 20 times faster, synthesizing audio in under one second. These results establish AudioGAN as a practical and powerful solution for real-time TTA.
format Preprint
id arxiv_https___arxiv_org_abs_2512_22166
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AudioGAN: A Compact and Efficient Framework for Real-Time High-Fidelity Text-to-Audio Generation
Chung, HaeChun
Sound
Audio and Speech Processing
Text-to-audio (TTA) generation can significantly benefit the media industry by reducing production costs and enhancing work efficiency. However, most current TTA models (primarily diffusion-based) suffer from slow inference speeds and high computational costs. In this paper, we introduce AudioGAN, the first successful Generative Adversarial Networks (GANs)-based TTA framework that generates audio in a single pass, thereby reducing model complexity and inference time. To overcome the inherent difficulties in training GANs, we integrate multiple ,contrastive losses and propose innovative components Single-Double-Triple (SDT) Attention and Time-Frequency Cross-Attention (TF-CA). Extensive experiments on the AudioCaps dataset demonstrate that AudioGAN achieves state-of-the-art performance while using 90% fewer parameters and running 20 times faster, synthesizing audio in under one second. These results establish AudioGAN as a practical and powerful solution for real-time TTA.
title AudioGAN: A Compact and Efficient Framework for Real-Time High-Fidelity Text-to-Audio Generation
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2512.22166