Papers › Compose & Embellish: Well-Structured Piano Performance Generation via A Two-Stage Approach

Compose & Embellish: Well-Structured Piano Performance Generation via A Two-Stage Approach

17 Sep 2022arXiv:2209.08212archive 2025-07-28

Shih-Lun Wu, Yi-Hsuan Yang

Even with strong sequence models like Transformers, generating expressive piano performances with long-range musical structures remains challenging. Meanwhile, methods to compose well-structured melodies or lead sheets (melody + chords), i.e., simpler forms of music, gained more success. Observing the above, we devise a two-stage Transformer-based framework that Composes a lead sheet first, and then Embellishes it with accompaniment and expressive touches. Such a factorization also enables pretraining on non-piano data. Our objective and subjective experiments show that Compose & Embellish shrinks the gap in structureness between a current state of the art and real performances by half, and improves other musical aspects such as richness and coherence as well.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 18 code samples harvested from 1 repository linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 18 samples from 1 repository, 17 ran (17 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

slseanwu/compose_and_embellish officialmentioned in papermentioned on GitHubpytorchMITSyntology: 18 samples, 17 ran (0 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

18 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

17ran
1unverified

Licence: 0 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from slseanwu/compose_and_embellish. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

slseanwu/compose_and_embellish official repository 18 samples, 17 ran (0 instrument-failed) · 1 unverified
check_extreme_pitch stage02_embellish/dataloader.py ran MIT (permissive) · bfc2a2bea1cae008 · report fixture: signature raw_events:list/1/dict · returned tuple · level recorded 2026-09-25
construct_inadmissible_set stage02_embellish/inference.py ran MIT (permissive) · 1684a40ef3af2d8c · report fixture: signature tempo_val:int/0/int, event2idx:dict/0/?, tolerance:int/0/int · returned ndarray · level recorded 2026-09-25
generate_bidirectional_pad_mask stage01_compose/model/transformer_helpers.py ran MIT (permissive) · 121b7194cf939651 · report fixture: signature max_seqlen:int/0/int, batch_lens:list/1/int · returned Tensor · level recorded 2026-09-25
generate_causal_mask in 6 papers stage01_compose/model/transformer_helpers.py ran MIT (permissive) · af1231b854ffe10c · report fixture: signature seq_len:int/0/int, device:str/0/str · returned Tensor · level recorded 2026-09-25
get_chord_tone stage01_compose/dataloader.py ran MIT (permissive) · fbaabefe1e3389f9 · report fixture: signature chord_event:str/0/str · returned str · level recorded 2026-09-25
get_chord_tone stage02_embellish/dataloader.py ran MIT (permissive) · 84f7aa7796be7bd4 · report fixture: signature chord_event:dict/0/? · returned int · level recorded 2026-09-25
get_min_max_pitch_idx stage01_compose/model/transformer_helpers.py ran MIT (permissive) · 2873fbbabe34e18e · report fixture: signature idx2event:dict/0/? · returned tuple · level recorded 2026-09-25
get_position_idx stage01_compose/inference_utils.py ran MIT (permissive) · b72c3b7bbc8073e4 · report fixture: signature event:str/0/str · returned int · level recorded 2026-09-25
numpy_to_tensor stage01_compose/utils.py ran MIT (permissive) · 8f85297926f9dfbd · report fixture: signature arr:ndarray/2/float, use_gpu:bool/0/bool · returned Tensor · level recorded 2026-09-25
pickle_load in 21 papers stage01_compose/utils.py ran MIT (permissive) · a452b37f41bd83f1 · report fixture: signature f:str/0/str · returned dict · level recorded 2026-09-25
read_generated_txt stage01_compose/convert2midi.py ran MIT (permissive) · a53f289be9ce8588 · report fixture: signature generated_path:str/0/str · returned list · level recorded 2026-09-25
roundup_enc_bar_arr_size stage01_compose/dataloader.py ran MIT (permissive) · 6441c139ab46f77b · report fixture: signature max_bar_len:int/0/int · returned int64 · level recorded 2026-09-25
temperature stage01_compose/inference_utils.py ran fingerprinted MIT (permissive) · 2a2fdbcc3e615d8c · report fixture: signature logits:ndarray/1/float, temperature:float/0/float · returned ndarray · level recorded 2026-09-25
temperature stage02_embellish/inference.py ran fingerprinted MIT (permissive) · cfcd4f3c8b9c03f3 · report fixture: signature logits:ndarray/1/float, temperature:float/0/float, inadmissibles:int/0/int · returned ndarray · level recorded 2026-09-25
tensor_to_numpy in 10 papers stage01_compose/utils.py ran MIT (permissive) · 5f9b99960db4d771 · report fixture: signature tensor:Tensor/2/float · returned ndarray · level recorded 2026-09-25
transpose_chord stage01_compose/dataloader.py ran MIT (permissive) · 2c1546244f2ecb37 · report fixture: signature chord_event:str/0/str, n_keys:int/0/int · returned str · level recorded 2026-09-25
transpose_chord stage02_embellish/dataloader.py ran MIT (permissive) · 6833bcfafc4a3a71 · report fixture: signature chord_event:dict/0/?, n_keys:int/0/int · returned dict · level recorded 2026-09-25
nucleus stage01_compose/inference_utils.py unverified MIT (permissive) · b21c0c2a2fec8283 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections