Výsledky vyhledávání - "Taylor, Josiah"

Report

Autor: Evans, Zach, Parker, Julian D., Carr, CJ, Zukowski, Zack, Taylor, Josiah, Pons, Jordi

Open generative models are vitally important for the community, allowing for fine-tunes and serving as baselines when presenting new models. However, most current text-to-audio models are private and not accessible for artists and researchers to buil

Externí odkaz: http://arxiv.org/abs/2407.14358

Zobrazit plný text záznamu

Report

Long-form music generation with latent diffusion

Autor: Evans, Zach, Parker, Julian D., Carr, CJ, Zukowski, Zack, Taylor, Josiah, Pons, Jordi

Audio-based generative models for music have seen great strides recently, but so far have not managed to produce full-length music tracks with coherent musical structure from text prompts. We show that by training a generative model on long temporal

Externí odkaz: http://arxiv.org/abs/2404.10301

Zobrazit plný text záznamu

Report

Fast Timing-Conditioned Latent Audio Diffusion

Autor: Evans, Zach, Carr, CJ, Taylor, Josiah, Hawley, Scott H., Pons, Jordi

Generating long-form 44.1kHz stereo audio from text prompts can be computationally demanding. Further, most previous works do not tackle that music and sound effects naturally vary in their duration. Our research focuses on the efficient generation o

Externí odkaz: http://arxiv.org/abs/2402.04825

Zobrazit plný text záznamu