AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

ComMU: Dataset for Combinatorial Music Generation

Lee Hyun, Taehyun Kim, Hyolim Kang, Minjoo Ki, Hyeonchan Hwang, Kwanho Park, Sharang Han, Seon Joo Kim

NeurIPS 2022 · Image generation › Autoregressive and latent generation · approach: Controllable music generation · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase sampling temperature from 0.7 to 1.2 (ablation)Transformer-XL on ComMU · ComMU validationdiversity (D): 0.2626 -> 0.3688Improved
increase sampling temperature from 0.7 to 1.2 (ablation)Transformer-XL on ComMU · ComMU validationpitch controllability (CP): 0.8798 -> 0.7721Hurt
increase sampling temperature from 0.7 to 1.2 (ablation)Transformer-XL on ComMU · ComMU validationvelocity controllability (CV): 0.9696 -> 0.8566Hurt
increase top-k from 32 to 200 at τ=0.95 (ablation)Transformer-XL on ComMU · ComMU validationpitch controllability (CP): 0.8412 -> 0.8488No clear effect
include key and BPM augmentation rather than no augmentation (ablation)Transformer-XL on ComMU · ComMU validationvelocity controllability (CV): 0.8194 -> 0.9102Improved
include key and BPM augmentation rather than no augmentation (ablation)Transformer-XL on ComMU · ComMU validationdiversity (D): 0.4386 -> 0.3160Hurt
use key augmentation only instead of key and BPM augmentation (ablation)Transformer-XL on ComMU · ComMU validationvelocity controllability (CV): 0.9102 -> 0.8663Hurt
use BPM augmentation only instead of key and BPM augmentation (ablation)Transformer-XL on ComMU · ComMU validationvelocity controllability (CV): 0.9102 -> 0.7615Hurt
use Transformer-GAN rather than Transformer-XL (ablation)ComMU generation · ComMU validationdiversity (D): 0.3160 -> 0.4097Improved
use Transformer-GAN rather than Transformer-XL (ablation)ComMU generation · ComMU validationvelocity controllability (CV): 0.9102 -> 0.8699Hurt
use REMI-style representation rather than MIDI-like representation (ablation)Transformer-XL · Subjective evaluationcontrollability: 2.53 -> 9.49Improved
increase representation resolution from 32 to 128 (ablation)Transformer-XL with REMI · Subjective evaluationoverall: 6.99 -> 7.31Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy