WavFlow: Audio Generation in Waveform Space
Modern 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.
Code (0)
등록된 구현이 없습니다.
Tasks
Audio GenerationSimilar Papers 제목 키워드 기반
It's Raw! Audio Generation with State-Space Models
Developing architectures suitable for modeling raw audio is a challenging problem due to the high sampling rates of audio waveforms. Standard sequence modeling approaches like RNNs and CNNs have previously been tailored …
Audio GenerationDensity EstimationMusic GenerationState Space ModelsAudio Super-Resolution with Latent Bridge Models
Audio super-resolution (SR), i.e., upsampling the low-resolution (LR) waveform to the high-resolution (HR) version, has recently been explored with diffusion and bridge models, while previous methods often suffer from su…
Audio Super-ResolutionDiffWave: A Versatile Diffusion Model for Audio Synthesis
In this work, we propose DiffWave, a versatile diffusion probabilistic model for conditional and unconditional waveform generation. The model is non-autoregressive, and converts the white noise signal into structured wav…
Audio SynthesisDiversitymodelSpeech SynthesisRAVE: A variational autoencoder for fast and high-quality neural audio synthesis
Deep generative models applied to audio have improved by a large margin the state-of-the-art in many speech and music related tasks. However, as raw waveform modelling remains an inherently difficult task, audio generati…
Audio SynthesisCPURepresentation LearningAdversarial Audio Synthesis
Audio signals are sampled at high temporal resolutions, and learning to synthesize audio requires capturing structure across a range of timescales. Generative adversarial networks (GANs) have seen wide success at generat…
Audio GenerationAudio SynthesisImage Generation