arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.00744cs.SDcs.CLeess.AS
收藏

BATON:利用人类偏好反馈对齐文本到音频模型

BATON: Aligning Text-to-Audio Model with Human Preference Feedback

Tsinghua University(清华大学);Huawei Technologies Co., Ltd.(华为技术有限公司)

Huan Liao, Haonan Han, Kai Yang, Tianjiao Du, Rui Yang, Zunnan Xu, Qinmei Xu, Jingquan Liu, Jiasheng Lu, Xiu Li

AI总结:

针对文本到音频模型生成内容难以对齐人类偏好的问题,提出包含数据集构建、奖励模型训练、模型微调三阶段的BATON框架,可显著提升生成音频的完整性、时间关系及人类偏好对齐度。

摘要:

随着人工智能生成内容(AIGC)的发展,文本到音频模型正受到广泛关注。然而,由于自然语言固有的信息密度以及模型理解能力有限,这些模型难以生成符合人类偏好的音频。为缓解这一问题,我们提出了BATON(一种利用人类偏好反馈增强生成音频与文本提示对齐度的框架)。我们的BATON包含三个核心阶段:首先,我们整理了一个包含提示词及对应生成音频的数据集,并基于人类反馈进行标注。其次,我们利用构建的数据集提出了一个奖励模型,该模型可通过为输入的文本-音频对分配奖励来模拟人类偏好。最后,我们使用该奖励模型对一个现成的文本到音频模型进行微调。实验结果表明,我们的BATON能够在音频完整性、时间关系以及与人类偏好的对齐度方面,显著提升原有文本到音频模型的生成质量。

英文摘要:

With the development of AI-Generated Content (AIGC), text-to-audio models are gaining widespread attention. However, it is challenging for these models to generate audio aligned with human preference due to the inherent information density of natural language and limited model understanding ability. To alleviate this issue, we formulate the BATON, a framework designed to enhance the alignment between generated audio and text prompt using human preference feedback. Our BATON comprises three key stages: Firstly, we curated a dataset containing both prompts and the corresponding generated audio, which was then annotated based on human feedback. Secondly, we introduced a reward model using the constructed dataset, which can mimic human preference by assigning rewards to input text-audio pairs. Finally, we employed the reward model to fine-tune an off-the-shelf text-to-audio model. The experiment results demonstrate that our BATON can significantly improve the generation quality of the original text-to-audio models, concerning audio integrity, temporal relationship, and alignment with human preference.

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。

↑