[obsidian] vault backup: 2025-06-13 10:14:35[
All checks were successful
Build / build (push) Successful in 8m53s
All checks were successful
Build / build (push) Successful in 8m53s
This commit is contained in:
@ -492,3 +492,31 @@ Cognitive musicology by [[Otto Laske]]
|
|||||||
|
|
||||||
[[Variable Marcov Oracle]]をマルチスケールに拡張したもの
|
[[Variable Marcov Oracle]]をマルチスケールに拡張したもの
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Deep Drawing
|
||||||
|
|
||||||
|
audio to drawing
|
||||||
|
|
||||||
|
絵を描いている時の音を録音して、その音から何を描いているのかコンピューターに予測させる
|
||||||
|
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## dit dah delta token: Statistical Models of Music and Language Interfering via Morse Code
|
||||||
|
|
||||||
|
|
||||||
|
[[Victor Shepardson]] [[Thor Magnusson]]
|
||||||
|
|
||||||
|
Morse music for LoftSkevtaStodin
|
||||||
|
|
||||||
|
[[Notochord]]
|
||||||
|
|
||||||
|
[[モールス信号]]
|
||||||
|
|
||||||
|
リズム・アンド・ランゲージモデル
|
||||||
|
|
||||||
|
LLMのトークンツリーの代わりにモールスツリーみたいなものを作る
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
12
content/Notochord.md
Normal file
12
content/Notochord.md
Normal file
@ -0,0 +1,12 @@
|
|||||||
|
---
|
||||||
|
date: 2025-06-13 09:56
|
||||||
|
---
|
||||||
|
#software
|
||||||
|
|
||||||
|
[[Victor Shepardson]]
|
||||||
|
|
||||||
|
[GitHub - Intelligent-Instruments-Lab/notochord: Notochord is a real-time neural network model for MIDI performances.](https://github.com/Intelligent-Instruments-Lab/notochord)
|
||||||
|
|
||||||
|
[Notochord | Intelligent Instruments Lab](https://iil.is/research/notochord)
|
||||||
|
|
||||||
|
|
10
content/Style Transfer.md
Normal file
10
content/Style Transfer.md
Normal file
@ -0,0 +1,10 @@
|
|||||||
|
---
|
||||||
|
date: 2025-06-13 09:23
|
||||||
|
---
|
||||||
|
#research #machinelearning
|
||||||
|
|
||||||
|
音楽分野でも結構あるのかな
|
||||||
|
|
||||||
|
[Groove2Groove – One-shot music style transfer](https://groove2groove.telecom-paris.fr/)
|
||||||
|
|
||||||
|
[MUSIC MIXING STYLE TRANSFER](https://jhtonykoo.github.io/MixingStyleTransfer/)
|
4
content/Thor Magnusson.md
Normal file
4
content/Thor Magnusson.md
Normal file
@ -0,0 +1,4 @@
|
|||||||
|
---
|
||||||
|
date: 2025-06-13 09:55
|
||||||
|
---
|
||||||
|
#person
|
6
content/Victor Shepardson.md
Normal file
6
content/Victor Shepardson.md
Normal file
@ -0,0 +1,6 @@
|
|||||||
|
---
|
||||||
|
date: 2025-06-13 09:57
|
||||||
|
---
|
||||||
|
#person
|
||||||
|
|
||||||
|
[jroose · GitHub](https://github.com/jroose)
|
19
content/機械学習とピッチ補正.md
Normal file
19
content/機械学習とピッチ補正.md
Normal file
@ -0,0 +1,19 @@
|
|||||||
|
---
|
||||||
|
date: 2025-06-13 09:20
|
||||||
|
---
|
||||||
|
#research #survey #machinelearning
|
||||||
|
|
||||||
|
[[知覚的擬似直接操作]]について考えていることの下調べ
|
||||||
|
|
||||||
|
[\[1902.00956\] Deep Autotuner: A Data-Driven Approach to Natural-Sounding Pitch Correction for Singing Voice in Karaoke Performances](https://arxiv.org/abs/1902.00956)
|
||||||
|
|
||||||
|
[[Sanna Wager]]
|
||||||
|
|
||||||
|
[DIFF-PITCHER: DIFFUSION-BASED SINGING VOICE PITCH CORRECTION](https://engineering.jhu.edu/lcap/data/uploads/pdfs/waspaa2023_hai.pdf)
|
||||||
|
|
||||||
|
[NEURAL PITCH-SHIFTING AND TIME-STRETCHING WITH CONTROLLABLE LPCNET](https://www.maxrmorrison.com/pdfs/morrison2022neural.pdf)
|
||||||
|
|
||||||
|
音楽における[[Style Transfer]]の特殊系と考えてもいいかも
|
||||||
|
|
||||||
|
|
||||||
|
|
Reference in New Issue
Block a user