Papers › Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed...

Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs

7 Jan 2021arXiv:2101.02402archive 2025-07-28

Wen-Yi Hsiao, Jen-Yu Liu, Yin-Cheng Yeh, Yi-Hsuan Yang

To apply neural sequence models such as the Transformers to music generation tasks, one has to represent a piece of music by a sequence of tokens drawn from a finite set of pre-defined vocabulary. Such a vocabulary usually involves tokens of various types. For example, to describe a musical note, one needs separate tokens to indicate the note's pitch, duration, velocity (dynamics), and placement (onset time) along the time grid. While different types of tokens may possess different properties, existing models usually treat them equally, in the same way as modeling words in natural languages. In this paper, we present a conceptually different approach that explicitly takes into account the type of the tokens, such as note types and metric types. And, we propose a new Transformer decoder architecture that uses different feed-forward heads to model tokens of different types. With an expansion-compression trick, we convert a piece of music to a sequence of compound words by grouping neighboring tokens, greatly reducing the length of the token sequences. We show that the resulting model can be viewed as a learner over dynamic directed hypergraphs. And, we employ it to learn to compose expressive Pop piano music of full-song length (involving up to 10K individual tokens per song), both conditionally and unconditionally. Our experiment shows that, compared to state-of-the-art models, the proposed model converges 5--10 times faster at training (i.e., within a day on a single GPU with 11 GB memory), and with comparable quality in the generated music.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2101.02402")

Code

Syntology Ran 3 of 9 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 3 ran with no contract checked.

By repository: community (archive-listed): 9 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

YatingMusic/compound-word-transformer officialmentioned in papermentioned on GitHubpytorch report
Natooz/MidiTok mentioned on GitHubpytorchMIT report
yuer867/emo-disentanger mentioned on GitHubpytorch 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

9 samples harvested; 3 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran
6unverified

Licence: 0 of the 9 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 yuer867/emo-disentanger. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

MultiHeadCrossAttn yuer867/emo-disentanger/stage1_compose/model/optimus_txl_decoder.py community (archive-listed) ran · metamorphic tier: invariant MIT (permissive) · e74a0089372f5f25 · report
RelPartialLearnableMultiHeadAttn yuer867/emo-disentanger/stage1_compose/model/optimus_txl_decoder.py community (archive-listed) ran MIT (permissive) · 8a40eebd3f2277dd · report
WordEmbedding yuer867/emo-disentanger/stage1_compose/model/optimus_txl_decoder.py community (archive-listed) ran · metamorphic tier: invariant MIT (permissive) · 169c0b8a3fa64163 · report
OptimusTXLDecoder yuer867/emo-disentanger/stage1_compose/model/optimus_txl_decoder.py community (archive-listed) unverified MIT (permissive) · 4e77f33db530a79a · report
RelLearnableDecoderLayer yuer867/emo-disentanger/stage1_compose/model/optimus_txl_decoder.py community (archive-listed) unverified MIT (permissive) · 1b3864723e0753c3 · report
RelLearnableMultiHeadAttn yuer867/emo-disentanger/stage1_compose/model/optimus_txl_decoder.py community (archive-listed) unverified MIT (permissive) · fa5d0870ee5677a9 · report
RelMultiHeadAttn yuer867/emo-disentanger/stage1_compose/model/optimus_txl_decoder.py community (archive-listed) unverified MIT (permissive) · f0aec7eb13b95e92 · report
RelPartialLearnableDecoderLayer yuer867/emo-disentanger/stage1_compose/model/optimus_txl_decoder.py community (archive-listed) unverified MIT (permissive) · bd98b4c481a677b5 · report
SegmentEmbeddingProj yuer867/emo-disentanger/stage1_compose/model/optimus_txl_decoder.py community (archive-listed) unverified MIT (permissive) · 65e3c462206adcba · report

Tasks

Music Generation

1 archive task tag without a task page not shown.

Datasets

Introduced by this paper, per the archive.

ailabs1k7

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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