Show HN: Catchy melodies made with a diffusion-based neural net assistant

38 points

4 years ago

I've created a diffusion-based neural net generative assistant that makes creating new melodies much easier, even for non-musicians like me. These are meant to be just the catchy "hook" parts of songs, so more work is required to make them into full songs, but this is already handled well by existing products (e.g. there are plugins that can suggest a few possible chord progressions based on the melody and there is even good singing software that I used without any tweaks to make the “voice” playlist: Synthesizer V Studio).

This side project turned out to be quite challenging because of how little data there is to train on - several orders of magnitude less than DALL-E or GPT-3 had available for its training, so it required a deep dive into research of new generalization and augmentation techniques and some feature engineering.

Various other instruments:

Voice: https://www.youtube.com/playlist?list=PLoCzMRqh5SkE1yC8_WtJ-...

Synth: https://www.youtube.com/playlist?list=PLoCzMRqh5SkFj7RNZvjr7...

Bell: https://www.youtube.com/playlist?list=PLoCzMRqh5SkEYHYvHX9m9...

Guitar: https://www.youtube.com/playlist?list=PLoCzMRqh5SkGKvfkP2Oex...

Sax: https://www.youtube.com/playlist?list=PLoCzMRqh5SkHfsZgzzdSh...

Grand Piano: https://www.youtube.com/playlist?list=PLoCzMRqh5SkFMch5x60uh...

SoundCloud electric piano: https://soundcloud.com/lech-mazur-995769534/sets/ai-assistan...

SoundCloud vocal: https://soundcloud.com/lech-mazur-995769534/sets/ai-assistan...

14 comments