Tango 2：通过直接偏好优化实现基于扩散的文本转音频生成的对齐

Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization

April 15, 2024

作者: Navonil Majumder, Chia-Yu Hung, Deepanway Ghosal, Wei-Ning Hsu, Rada Mihalcea, Soujanya Poria

cs.AI

摘要

生成式多模态内容在内容创作领域越来越普遍，因为它有潜力让艺术家和媒体人员通过快速将他们的想法具体化来创建预制作模型。从文本提示生成音频是音乐和电影行业中这类过程的重要方面。许多最近基于扩散的文本转音频模型侧重于在大量数据集上训练越来越复杂的扩散模型，这些数据集包含提示-音频对。这些模型并未明确关注输出音频中与输入提示相关的概念或事件的存在以及它们的时间顺序。我们的假设是关注音频生成中这些方面如何在有限数据的情况下提高音频生成性能。因此，在这项工作中，我们使用现有的文本转音频模型Tango，合成创建了一个偏好数据集，其中每个提示都有一个获胜音频输出和一些失败音频输出，供扩散模型学习。理论上，失败输出中的一些概念可能缺失或顺序不正确。我们使用扩散-DPO（直接偏好优化）损失在我们的偏好数据集上对公开可用的Tango文本转音频模型进行微调，并表明这导致音频输出在自动和手动评估指标方面优于Tango和AudioLDM2。

English

Generative multimodal content is increasingly prevalent in much of the content creation arena, as it has the potential to allow artists and media personnel to create pre-production mockups by quickly bringing their ideas to life. The generation of audio from text prompts is an important aspect of such processes in the music and film industry. Many of the recent diffusion-based text-to-audio models focus on training increasingly sophisticated diffusion models on a large set of datasets of prompt-audio pairs. These models do not explicitly focus on the presence of concepts or events and their temporal ordering in the output audio with respect to the input prompt. Our hypothesis is focusing on how these aspects of audio generation could improve audio generation performance in the presence of limited data. As such, in this work, using an existing text-to-audio model Tango, we synthetically create a preference dataset where each prompt has a winner audio output and some loser audio outputs for the diffusion model to learn from. The loser outputs, in theory, have some concepts from the prompt missing or in an incorrect order. We fine-tune the publicly available Tango text-to-audio model using diffusion-DPO (direct preference optimization) loss on our preference dataset and show that it leads to improved audio output over Tango and AudioLDM2, in terms of both automatic- and manual-evaluation metrics.