Generating Music Tracks with Unified Representation and Diffusion Framework

Re:Generating Music Tracks with Unified Representation and D... by bandika on Tuesday May 23, 2023 @05:10AM (#36041763)

Musically, those examples are really bland, and the rendering is of poor quality.

Besides, I'm not sure what's the point of this. I can see how ChatGPT can be useful for devs/writers/researchers etc. I can't imagine how this could be useful for a musician.

[ Parent | on HN ]

Re:Generating Music Tracks with Unified Representation and D... by AlecSchueler on Tuesday May 23, 2023 @05:42AM (#36041969)

To be fair some people have already listed examples of how they could use the technology elsewhere in the thread, and it will only improve from this point.

[ Parent | on HN ]

Re:Generating Music Tracks with Unified Representation and D... by laratied on Tuesday May 23, 2023 @06:11AM (#36042120)

I can't wait for better music AI but these examples are absolutely pathetic.

It is shameful to mention Bach's name in that one example.

[ Parent | on HN ]

Re:Generating Music Tracks with Unified Representation and D... by ad8e on Tuesday May 23, 2023 @10:50PM (#36053494)

Contrast this parent comment's opinion, that it is "shameful to mention Bach's name" with the Bach example, with this comment https://news.ycombinator.com/item?id=36043384, pointing out that the Bach example is plagiarized from Bach: https://www.youtube.com/watch?v=Fpqd1gCzLN4&t=178s

[ Parent | on HN ]