News for hackers. Stuff that matters.

A comment on Show HN: Cloning a musical instrument from 16 seconds of audio.

Re:Show HN: Cloning a musical instrument from 16 seconds of ... by nyanpasu64 on Friday February 25, 2022 @04:20PM (#30472509)
Does this work on synthesized sounds (like analog or physical modeling rather than samplers)? How does it handle the complexity of piano timbres (notoriously difficult to synthesize)?
[ Parent | on HN ]
Re:Show HN: Cloning a musical instrument from 16 seconds of ... by abdljasser2 on Friday February 25, 2022 @07:21PM (#30474063)
Great question! I think this approach (and DDSP more generally) could work well for most instruments if you make some adjustments to the synthesis architecture.

The current architecture imposes some strong assumptions on the source (such as harmonicity) which does not necessarily apply to all instruments (bells for instance). The harmonic + noise model is not that good with transients either (which is a key ingredient in piano sounds) but of course you could solve that through different means.

[ Parent | on HN ]