[HN Gopher] Cassiopeia: New Audio Splitter Superior to Spleeter ...
___________________________________________________________________
Cassiopeia: New Audio Splitter Superior to Spleeter and UMX
Author : ofou
Score : 38 points
Date : 2021-10-23 08:57 UTC (14 hours ago)
(HTM) web link (www.lalal.ai)
(TXT) w3m dump (www.lalal.ai)
| abetusk wrote:
| Spleeter and UMX are both FOSS [0] [1], whereas, as far as I can
| tell, Cassiopeia is not.
|
| [0] https://github.com/deezer/spleeter/blob/master/LICENSE
|
| [1] https://github.com/sigsep/open-unmix-pytorch
| CharlesW wrote:
| And since they're comparing closed source offerings, it seems
| notable that iZotope RX (which can isolate not just vocals but
| also percussion and bass) isn't in the mix.
| sdenton4 wrote:
| Is there a paper on how they're resynthesizing phase components?
| IME neutral networks are real real bad at handling fft phase, so
| separation tend to use frequency making, or use a learned filter
| bank.
| gavinray wrote:
| There's maybe something useful for you here?
|
| https://github.com/facebookresearch/demucs
|
| https://github.com/sigsep/open-unmix-pytorch
|
| https://github.com/bytedance/music_source_separation
|
| https://github.com/deezer/spleeter
| sdenton4 wrote:
| Looks like demucs is using a learned filter bank (so no
| handling of fft phase), and open umix and spleeter are using
| spectrogram magnitude masking (just reuse phase from original
| fft in all channels). Can't immediately tell what bytedance
| is doing.
| gavinray wrote:
| I know this comes off as "Eugh, that guy"
|
| And I don't mean it this way.
|
| But from a marketing standpoint, "Audio Splitter" is probably not
| the term you want to use for this.
|
| I only knew what this was because of frequently using Spleeter,
| Demucs, OpenUnmix etc to do Music Source Separation for hobbyist
| electronic music production on weekends.
|
| "Audio Splitter" made me think it was some hardware device for
| redirecting audio streams. Like the thing that let's you connect
| multiple headphones to one jack.
|
| For technical folk, the term they're probably searching is "Music
| Source Separation"
|
| For audio folk, it's likely "Automatic stem extraction/isolation"
|
| To the layperson, I'm not sure -- "How to convert song into
| individual parts"?
|
| Last point I have no issue with: but you may face some hurdles
| due to the rest of this research area being very transparent and
| OSS.
| herodotus wrote:
| How well would this kind of splitter work for Opera? I suspect
| that the separation problem is significantly more difficult.
___________________________________________________________________
(page generated 2021-10-23 23:02 UTC)