推起來

🎉We are happy to introduce #DiffARiff our new AI model that create instrumental accompaniments for your music. 🎼Whether you're a musician looking for inspiration or just curious about #AI in music, Diff-A-Riff opens up exciting new possibilities! 🔽 Video, paper & more info!

DisMix is accepted to the NeurIPS Conference Audio Imagination Workshop audio-imagination.com. Thanks my collaborators throughout the internship, and special shoutouts to Keitaro Tanaka for initial discussions on the topic. Audio samples are at yjlolo.github.io/dismix-audio-s…

I just made a little app where you can upload a music file; and then it uses AI to automagically transcribe the chord progression and then let you play along in real-time. great for learning and practicing new songs! at me if you want to use this

Audio codecs are turning into VQ-based voice conversion models with an extra focus on compression. Disentanglement seems to be the sauce.

We built a hierarchical generative model to sing Hindustani vocal melodies 🎤! We will be presenting this work at ISMIR 2024! ISMIR Conference 📝Paper: arxiv.org/abs/2408.12658 💻Code: github.com/snnithya/GaMaD… 👩🏽‍💻Demo: huggingface.co/spaces/snnithy… 🎧Samples: snnithya.github.io/gamadhani-samp…

v4 is coming soon 🎧

New project test Use an Neural Audio Codec AI model to regen my music stems #AI #AImusic

Ello