🥳Excited to share our latest work: "Diff-A-Riff"! 🥁
@deeplearnmusic1635 位关注者
17,760 次观看
10 条评论
评论来自 X (Twitter) 上的原帖

@deeplearnmusic
Update! 🥳 This example demonstrates how to produce a song with Diff-A-Riff starting from a simple template and adding one instrument at a time:
7 个赞

@AltRealityGameX
Can't wait to kick this around. So glad to see all the new accomapaniment stuff coming out. This conrner of the tech. Accompaniment, trained musician agents, working towards realtime interactive "jamming" to vibe with automation that doesn't feel like just playing with a looper!
5 个赞

@MAChirrups
Very cool stuff!
3 个赞

@devinarne
Congratulations! This is an amazing tool, the one stem at a time approach is great for musicians/producers as it gives granular control. I could also see this as helpful for film/TV composers to make variations on themes and cues. Hope to be able to use this in the near future!
3 个赞

@JanneSpijkervet
Now this is exciting!! Well done! Two questions came to mind after a first glance: 1) 50% dropout on audio/CLAP conditioning appeared high to me, was this required? And 2) the impact of the CAE (I’m impressed by the decoder at that number of params!) Nice work!
3 个赞

@florianvo
Wow! That sounds impressive :)
3 个赞

@matangover
Awesome work, great results!! One question about inpainting - in the demo audios, the inpainting result sounds slightly different than the original, even in the non-masked region. Is this due to CAE roundtrip?
1 个赞

@234Sagyboy
@deeplearnmusic Interesting I would love and appreciate to see a similar type of work with tts please look into it Thankyou so much
1 个赞

@gregorylent
@MacTuitui can i mix the output? delete tracks? change levels ??

@deeplearnmusic
@MacTuitui Hi Gregory! The model adds one track at a time, giving the user full control over the mix.
2 个赞