arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2401.01044cs.SDcs.AIcs.CLeess.AS
收藏

Auffusion:利用扩散模型和大型语言模型的强大能力进行文本到音频生成

Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation

Beijing University of Posts and Telecommunications(北京邮电大学)

Jinlong Xue, Yayue Deng, Yingming Gao, Ya Li

AI总结:

本文提出Auffusion系统,通过将文本到图像扩散模型框架适配到文本到音频任务,有效利用其生成优势和跨模态对齐能力,在有限数据和计算资源下超越现有方法,并通过消融研究和可视化评估了文本-音频对齐性能。

摘要:

扩散模型和大型语言模型(LLMs)的最新进展显著推动了AIGC领域的发展。文本到音频(TTA)是一种旨在从自然语言提示生成音频的新兴AIGC应用,正吸引越来越多的关注。然而,现有的TTA研究在生成质量和文本-音频对齐方面常常遇到困难,特别是对于复杂的文本输入。从最先进的文本到图像(T2I)扩散模型中汲取灵感,我们引入了Auffusion,这是一个通过有效利用其固有的生成优势和精确的跨模态对齐,将T2I模型框架适应到TTA任务的TTA系统。我们的客观和主观评估表明,Auffusion在使用有限数据和计算资源的情况下超越了以前的TTA方法。此外,以前在T2I中的研究认识到编码器选择对跨模态对齐(如细粒度细节和对象绑定)的显著影响,而以前的TTA工作中缺乏类似的评估。通过全面的消融研究和创新的交叉注意力图可视化,我们对TTA中的文本-音频对齐提供了有见地的评估。我们的发现揭示了Auffusion在生成准确匹配文本描述的音频方面的卓越能力,这在几个相关任务中得到了进一步证明,如音频风格迁移、修复和其他操作。我们的实现和演示可在https://auffusion.github.io获取。

英文摘要:

Recent advancements in diffusion models and large language models (LLMs) have significantly propelled the field of AIGC. Text-to-Audio (TTA), a burgeoning AIGC application designed to generate audio from natural language prompts, is attracting increasing attention. However, existing TTA studies often struggle with generation quality and text-audio alignment, especially for complex textual inputs. Drawing inspiration from state-of-the-art Text-to-Image (T2I) diffusion models, we introduce Auffusion, a TTA system adapting T2I model frameworks to TTA task, by effectively leveraging their inherent generative strengths and precise cross-modal alignment. Our objective and subjective evaluations demonstrate that Auffusion surpasses previous TTA approaches using limited data and computational resource. Furthermore, previous studies in T2I recognizes the significant impact of encoder choice on cross-modal alignment, like fine-grained details and object bindings, while similar evaluation is lacking in prior TTA works. Through comprehensive ablation studies and innovative cross-attention map visualizations, we provide insightful assessments of text-audio alignment in TTA. Our findings reveal Auffusion's superior capability in generating audios that accurately match textual descriptions, which further demonstrated in several related tasks, such as audio style transfer, inpainting and other manipulations. Our implementation and demos are available at https://auffusion.github.io.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑