Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization

arXiv:2404.09956v1 Announce Type: cross
Abstract: Generative multimodal content is increasingly prevalent in much of the content creation arena, as it has the potential to allow artists and media personnel to create pre-production mockups by quickly bringing their ideas to life. The generation of audio from text prompts is an important aspect of such processes in the music and film industry. Many of the recent diffusion-based text-to-audio models focus on training increasingly sophisticated diffusion models on a large set of datasets …

abstract arena artists arxiv audio create cs.ai cs.cl cs.sd diffusion direct preference optimization eess.as generative ideas life media multimodal multimodal content optimization production prompts text through type