EDMSound: Spectrogram Based Diffusion Models for Efficient and High-Quality Audio Synthesis

Ge Zhu, Yutong Wen, Marc-André Carbonneau, Zhiyao Duan

EDMSound: Spectrogram Based Diffusion Models for Efficient and High-Quality Audio Synthesis: 18 upvotes on Hugging Face Daily Papers, #4 of 13 papers on 2023-11-16. Day-by-day upvote history.

Audio diffusion models can synthesize a wide variety of sounds. Existing models often operate on the latent domain with cascaded phase recovery modules to reconstruct waveform. This poses challenges when generating high-fidelity audio. In this paper, we propose EDMSound, a diffusion-based generative model in spectrogram domain under the framework of elucidated diffusion models (EDM). Combining with efficient deterministic sampler, we achieved similar Fr\'echet audio distance (FAD) score as top-ranked baseline with only 10 steps and reached state-of-the-art performance with 50 steps on the DCASE2023 foley sound generation benchmark. We also revealed a potential concern regarding diffusion based audio generation models that they tend to generate samples with high perceptual similarity to the data from training data. Project page: https://agentcooper2002.github.io/EDMSound/

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.