titleWavFlow: Audio Generation in Waveform Space
authorsFeiyan Zhou, Luyuan Wang, Shoufa Chen, Zhe Wang, Zhiheng Liu, Yuren Cong, Xiaohui Zhang, Fanny Yang, Belinda Zeng
date2026-05-18
venuearXiv (preprint, not peer reviewed)
idarXiv:2605.18749
affiliationMeta Research
upvotes4 (Hugging Face Daily Papers, 2026-11-01)
linksabs pdf hf code
abstractModern audio generation predominantly relies on latent-space compression, introducing additional complexity and potential information loss. In this work, we challenge this paradigm with WavFlow, a framework that generates high-fidelity audio directly in raw waveform space without intermediate representations. To overcome the inherent difficulties of modeling high-dimensional and low-energy signals, we reshape audio into 2D token grids through waveform patchify and introduce amplitude lifting to align signal scales, enabling stable optimization via direct x-prediction in flow matching. To capture complex semantic alignment and temporal synchronization, we leverage an automated data pipeline to curate 5 million high-quality video-text-audio triplets, allowing the model to learn fine-grained acoustic patterns from scratch. Experimental results show that WavFlow achieves competitive performance on the video-to-audio benchmark VGGSound (FD_PaSST: 59.98, IS_PANNs: 17.40, DeSync: 0.44) and the text-to-audio benchmark AudioCaps (FD_PANNs: 10.63, IS_PANNs: 12.62), matching or exceeding the performance of established latent-based methods. Our work demonstrates that intermediate compression is not a prerequisite for high-quality synthesis, offering a simpler and more scalable alternative for multimodal audio generation.

cite

@misc{zhou2026wavflow,
  title={WavFlow: Audio Generation in Waveform Space},
  author={Feiyan Zhou and Luyuan Wang and Shoufa Chen and Zhe Wang and Zhiheng Liu and Yuren Cong and Xiaohui Zhang and Fanny Yang and Belinda Zeng},
  year={2026},
  eprint={2605.18749},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2605.18749}
}