T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback
Zehan Wang, Ke Lei, Chen Zhu, Jiawei Huang, Sashuai Zhou, Luping Liu, Xize Cheng, Shengpeng Ji, Zhenhui Ye, Tao Jin, Zhou Zhao
摘要
Figure 1 : The audio description is from a classic Chinese essay "Kou Ji", which vividly depicts a performer using only vocal mimicry to recreate an entire dramatic scene. The existing Text-to-Audio generation model struggles to generate such narrative and multi-event audios. The generated audio often fails to contain all events in the described sequence while maintaining acoustic quality and harmony.
问 Lune
尽管问，回答会引用原文。
Lune 会读完全文和相关的 Paper，每个回答都附上所依据的原文段落。
引用它的顶会 Paper1
它引用的 Paper8
- Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image GenerationYuval Kirstain, Adam Polyak, Uriel Singer, Shahbuland Matiana 等NeurIPS 2023 · 1,192 次引用
- Self-Rewarding Language ModelsWeizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho, Xian Li 等ICML 2024 · 569 次引用
- BEATs: Audio Pre-Training with Acoustic TokenizersSanyuan Chen, Yu Wu, Chengyi Wang, Shujie Liu 等ICML 2023 · 568 次引用
- Masked Autoencoders that ListenPo-Yao Huang, Hu Xu, Juncheng Li, Alexei Baevski 等NeurIPS 2022 · 524 次引用
- Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak SupervisionCollin Burns, Pavel Izmailov, Jan Hendrik Kirchner, Bowen Baker 等ICML 2024 · 443 次引用
相关 Paper
- AudioStory: Generating Long-Form Narrative Audio with Large Language ModelsYuxin Guo, Teng Wang, Yuying Ge, Shijie Ma 等CVPR 2026 · 5 次引用
- Text-to-Audio Generation using Instruction Guided Latent Diffusion ModelDeepanway Ghosal, Navonil Majumder, Ambuj Mehrish, Soujanya PoriaACM MM 2023 · 90 次引用
- MM-Narrator: Narrating Long-form Videos with Multimodal In-Context LearningChaoyi Zhang, Kevin Lin, Zhengyuan Yang, Jianfeng Wang 等CVPR 2024 · 20 次引用
- MCGA: A Multi-task Classical Chinese Literary Genre Audio CorpusYexing Du, Kaiyuan Liu, Bihe Zhang, Youcheng Pan 等ACL Findings 2026
- Fine-grained Audible Video DescriptionXuyang Shen, Dong Li, Jinxing Zhou, Zhen Qin 等CVPR 2023
