Is anyone aware of any AI/ML/DL learning projects related to audio.

Is anyone aware of any AI/ML/DL projects related to audio.

There is plethora of AI/ML/DL projects for video like deepkfaes, image generation through text, upscaling, etc. But I can’t seem to find any such projects for audio, I want to learn about them to see if they can be used to make subliminal.

Real-time accent replacement … https://youtu.be/ur28EpG9CR0

I don’t think this will help in anyway in creating subliminal. What other projects are there for audio?