🔬The science behind noiseGPT

Further reading:

High quality voice conversion using prosodic and high-resolution spectral features https://arxiv.org/pdf/1512.01809.pdf

Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation https://arxiv.org/abs/2211.06687

Contrastive Pre-training of Visual-Language Models https://towardsdatascience.com/contrastive-pre-training-of-visual-language-models-848dd94c881b