2025:Symbolic Music Generation Results

2026-07-01T10:12:17Z

Xinyue2896:

= Submissions =

{| class="wikitable"
|- style="font-weight:bold;"
! Team
! Extended Abstract
! Methods
|-
| RWKV (Zhou-Zheng et al.)
| [http://futuremirex.com/portal/wp-content/uploads/2025/symbolic-music-generation/RWKV.pdf PDF]
| RWKV
|-
| PixelGen
| [http://futuremirex.com/portal/wp-content/uploads/2025/symbolic-music-generation/PixelGen.pdf PDF]
| Hierarchical Transformer
|-
| MuseCoco (BL-1)
| [https://arxiv.org/abs/2306.00110]
| Transformer
|-
| Anticipatory Music Transformer (BL-2)
| [https://arxiv.org/abs/2306.08620]
| Transformer
|-
|}

=Results=

{| class="wikitable" style="text-align:center;"
|- style="font-weight:bold; vertical-align:center;"
! rowspan="2" | Team
! colspan="4" | Subjective Evaluation
|- style="font-weight:bold; vertical-align:center;"
| Coherecy ↑
| Structure ↑
| Creativity ↑
| Musicality ↑
|-
| RWKV (Zhou-Zheng et al.)
| 3.57 ± 0.10a
| 3.58 ± 0.10a
| 3.26 ± 0.10a
| '''3.50 ± 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 ± 0.10a'''
| '''3.69 ± 0.09a'''
| '''3.30 ± 0.10a'''
| 3.45 ± 0.10a
|}

'''Evaluation Results'''

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 with Holm-Bonferroni correction.

'''Baseline Models'''

For MuseCoco, we use the ''xlarge'' model with 1.2 billion learnable parameters. For Anticipatory Music Transformer, we use the ''Large'' model with 780M learnable parameters.

'''Subjective Evaluation Details'''

A double-blind online survey was conducted to test music quality. Each model was anonymised, and for each test prompt, a sample was cherry-picked from 8 generated candidates. A total of 8 prompts of varied styles (pop, classical, and jazzy) were tested, resulting in an 8-page survey. The page order and the sample order within each page were both randomised.

Responses were collected from 20 participants with diverse music backgrounds. 14 participants completed all 8 pages with an average completion time of 32 minutes.

= Listening Samples =
Play-along piano-roll continuations (visual + audio) for every prompt and system are available on the demo page:

: '''[https://futuremirex.com/demos/symbolic-music-generation/ ▶ Open the interactive demo]'''

MIREX Wiki - User contributions [en]

2025:Symbolic Music Generation Results