====== Differences ====== This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
realtime_solo-to-tutti_audio_alignment_separation-by-humming_for_realtime_karaoke_generation [2014/10/26 04:23] maezawa |
realtime_solo-to-tutti_audio_alignment_separation-by-humming_for_realtime_karaoke_generation [2014/10/26 05:21] (current) maezawa |
||
---|---|---|---|
Line 1: | Line 1: | ||
+ | ====== Karaoke on Your Favorite Recording... without a SMF! ====== | ||
+ | |||
====== Background ====== | ====== Background ====== | ||
Automatic accompaniment (e.g. a karaoke that follows your playing) kicks ass. | Automatic accompaniment (e.g. a karaoke that follows your playing) kicks ass. | ||
Line 53: | Line 55: | ||
Aside 1: Elaborate schemes using semi-HMM wasn't worth the effort, at least for simple duration pdf. | Aside 1: Elaborate schemes using semi-HMM wasn't worth the effort, at least for simple duration pdf. | ||
- | Aside 2: I tried first modeling the state dynamics using Particle filter (like Montecchio2011, Ohtsuka2011) | + | Aside 2: I tried first modeling the state dynamics using Particle filter but it didn't quite work. With finite particles, once it gets "stuck," simple proposal distribution |
- | but it didn't quite work. With finite particles, once it gets "stuck," simple proposal distribution | + | |
is insufficient to recover the right position. | is insufficient to recover the right position. | ||