2025:Symbolic Music Generation Results

From MIREX Wiki
Revision as of 22:24, 10 September 2025 by Zizzi wang (talk | contribs) (Created page with " = Submissions = {| class="wikitable" |- style="font-weight:bold;" ! Team ! Extended Abstract ! Methods |- | RWKV (Zhou-Zheng et al.) | [https://www.music-ir.org/mirex/wiki/...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Submissions

Team Extended Abstract Methods
RWKV (Zhou-Zheng et al.) [1] RWKV
PixelGen [2] Hierarchical Transformer
MuseCoco (BL-1) [3] Transformer
Anticipatory Music Transformer (BL-2) [4] Transformer

Results

Team Subjective Evaluation
Coherecy ↑ Structure ↑ Creativity ↑ Musicality ↑
RWKV (Zhou-Zheng et al.) 3.57 ± 0.10a 3.58 ± 0.10a 3.26 ± 0.10a 3.5 ± 0.10a
PixelGen 2.39 ± 0.10c 2.37 ± 0.09c 2.85 ± 0.09b 2.48 ± 0.09c
MuseCoco (BL-1) 3.11 ± 0.10b 3.07 ± 0.09b 3.08 ± 0.09ab 2.95 ± 0.09b
Anticipatory Music Transformer (BL-2) 3.70 ± 0.10c 3.69 ± 0.09b 3.30 ± 0.10b 3.45 ± 0.10b

Note: Results are reported in the form of mean ± sems (sem refers to standard error of mean), where s is a letter. Different letters within a column indicate significant differences (p-value p < 0.05) based on a Wilcoxon signed rank test.

Objective Evaluation Details: Each model generates 16 samples for each of 6 test pieces. Negative Log Likelihood (NLL) is computed by inputing the molody and accompaniment into the MuseCoco 1B model.

Subjective Evaluation Details: One piece cherry-picked from 16 samples of each test piece, resulting in 6 pages of questions. We collect responses from 22 participants (18 complete submissions and 4 partial submissions). For complete submissions, the average completion time is 16min 59s.