Zero Shot Audio Style Transfer

via “zero-shot audio style transfer”

* ⭐ 03/2023: [Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages (USM)](https://arxiv.org/abs/2303.01037)

Unique: First text-to-audio system to enable zero-shot audio style manipulation by conditioning diffusion on CLAP embeddings of style descriptions, avoiding need for paired training data of source-target style examples

vs others: Eliminates requirement for paired training data on specific style transformations (unlike traditional style transfer), enabling arbitrary style descriptions via natural language rather than predefined style categories

via “voice-style-transfer”