Hierarchical Symbolic Pop Music Generation with Graph Neural Networks Article Swipe
Lim, Wen Qing
,
Liang Jin-hua
,
Zhang Huan
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.5281/zenodo.17488857
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.5281/zenodo.17488857
Music is inherently made up of complex structures, and representing them as graphs helps to capture multiple levels of relationships. While music generation has been explored using various deep generation techniques, research on graph-related music generation is sparse. Earlier graph-based music generation worked only on generating melodies, and recent works to generate polyphonic music do not account for longer-term structure. In this paper, we explore a multi-graph approach to represent both the rhythmic patterns and phrase structure of Chinese pop music. Consequently, we propose a two-step approach that aims to generate polyphonic music with coherent rhythm and long-term structure. We train two Variational Auto-Encoder networks: one on a MIDI dataset to generate 4-bar phrases, and another on song structure labels to generate full song structure. Our work shows that the models are able to learn most of the structural nuances in the training dataset, including chord and pitch frequency distributions, and phrase attributes.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.5281/zenodo.17488857
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W7103893500
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W7103893500Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.5281/zenodo.17488857Digital Object Identifier
- Title
-
Hierarchical Symbolic Pop Music Generation with Graph Neural NetworksWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-11-03Full publication date if available
- Authors
-
Lim, Wen Qing, Liang Jin-hua, Zhang HuanList of authors in order
- Landing page
-
https://doi.org/10.5281/zenodo.17488857Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.5281/zenodo.17488857Direct OA link when available
- Concepts
-
Chord (peer-to-peer), MIDI, Polyphony, Computer science, Phrase, Popular music, Rhythm, Speech recognition, Artificial intelligence, Graph, Harmony (Music), Artificial neural network, Pop music automation, Recurrent neural network, Melody, Natural language processing, SpectrogramTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W7103893500 |
|---|---|
| doi | https://doi.org/10.5281/zenodo.17488857 |
| ids.doi | https://doi.org/10.5281/zenodo.17488857 |
| ids.openalex | https://openalex.org/W7103893500 |
| fwci | 0.0 |
| type | article |
| title | Hierarchical Symbolic Pop Music Generation with Graph Neural Networks |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11349 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.5400663614273071 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1707 |
| topics[0].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[0].display_name | Music Technology and Sound Studies |
| topics[1].id | https://openalex.org/T11309 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.1770952045917511 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1711 |
| topics[1].subfield.display_name | Signal Processing |
| topics[1].display_name | Music and Audio Processing |
| topics[2].id | https://openalex.org/T11574 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.07137089222669601 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Artificial Intelligence in Games |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C194147245 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8658267259597778 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1076368 |
| concepts[0].display_name | Chord (peer-to-peer) |
| concepts[1].id | https://openalex.org/C8112396 |
| concepts[1].level | 2 |
| concepts[1].score | 0.8080606460571289 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q80535 |
| concepts[1].display_name | MIDI |
| concepts[2].id | https://openalex.org/C128979739 |
| concepts[2].level | 2 |
| concepts[2].score | 0.7194115519523621 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q179465 |
| concepts[2].display_name | Polyphony |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.6992395520210266 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C2776224158 |
| concepts[4].level | 2 |
| concepts[4].score | 0.6465532183647156 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q187931 |
| concepts[4].display_name | Phrase |
| concepts[5].id | https://openalex.org/C114611597 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5531015992164612 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q373342 |
| concepts[5].display_name | Popular music |
| concepts[6].id | https://openalex.org/C135343436 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5506688952445984 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q170406 |
| concepts[6].display_name | Rhythm |
| concepts[7].id | https://openalex.org/C28490314 |
| concepts[7].level | 1 |
| concepts[7].score | 0.49143949151039124 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q189436 |
| concepts[7].display_name | Speech recognition |
| concepts[8].id | https://openalex.org/C154945302 |
| concepts[8].level | 1 |
| concepts[8].score | 0.44180190563201904 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[8].display_name | Artificial intelligence |
| concepts[9].id | https://openalex.org/C132525143 |
| concepts[9].level | 2 |
| concepts[9].score | 0.37151840329170227 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q141488 |
| concepts[9].display_name | Graph |
| concepts[10].id | https://openalex.org/C89721942 |
| concepts[10].level | 3 |
| concepts[10].score | 0.37030306458473206 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q184421 |
| concepts[10].display_name | Harmony (Music) |
| concepts[11].id | https://openalex.org/C50644808 |
| concepts[11].level | 2 |
| concepts[11].score | 0.34963929653167725 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[11].display_name | Artificial neural network |
| concepts[12].id | https://openalex.org/C73520026 |
| concepts[12].level | 4 |
| concepts[12].score | 0.3316885530948639 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q7229091 |
| concepts[12].display_name | Pop music automation |
| concepts[13].id | https://openalex.org/C147168706 |
| concepts[13].level | 3 |
| concepts[13].score | 0.3172050714492798 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q1457734 |
| concepts[13].display_name | Recurrent neural network |
| concepts[14].id | https://openalex.org/C43803900 |
| concepts[14].level | 3 |
| concepts[14].score | 0.31711915135383606 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q170412 |
| concepts[14].display_name | Melody |
| concepts[15].id | https://openalex.org/C204321447 |
| concepts[15].level | 1 |
| concepts[15].score | 0.31574875116348267 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[15].display_name | Natural language processing |
| concepts[16].id | https://openalex.org/C45273575 |
| concepts[16].level | 2 |
| concepts[16].score | 0.2760322391986847 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q578970 |
| concepts[16].display_name | Spectrogram |
| keywords[0].id | https://openalex.org/keywords/chord |
| keywords[0].score | 0.8658267259597778 |
| keywords[0].display_name | Chord (peer-to-peer) |
| keywords[1].id | https://openalex.org/keywords/midi |
| keywords[1].score | 0.8080606460571289 |
| keywords[1].display_name | MIDI |
| keywords[2].id | https://openalex.org/keywords/polyphony |
| keywords[2].score | 0.7194115519523621 |
| keywords[2].display_name | Polyphony |
| keywords[3].id | https://openalex.org/keywords/phrase |
| keywords[3].score | 0.6465532183647156 |
| keywords[3].display_name | Phrase |
| keywords[4].id | https://openalex.org/keywords/popular-music |
| keywords[4].score | 0.5531015992164612 |
| keywords[4].display_name | Popular music |
| keywords[5].id | https://openalex.org/keywords/rhythm |
| keywords[5].score | 0.5506688952445984 |
| keywords[5].display_name | Rhythm |
| keywords[6].id | https://openalex.org/keywords/graph |
| keywords[6].score | 0.37151840329170227 |
| keywords[6].display_name | Graph |
| language | en |
| locations[0].id | doi:10.5281/zenodo.17488857 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400562 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Zenodo (CERN European Organization for Nuclear Research) |
| locations[0].source.host_organization | https://openalex.org/I67311998 |
| locations[0].source.host_organization_name | European Organization for Nuclear Research |
| locations[0].source.host_organization_lineage | https://openalex.org/I67311998 |
| locations[0].license | cc-by |
| locations[0].pdf_url | |
| locations[0].version | |
| locations[0].raw_type | |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | False |
| locations[0].is_published | |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://doi.org/10.5281/zenodo.17488857 |
| indexed_in | datacite |
| authorships[0].author.id | |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Lim, Wen Qing |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Lim, Wen Qing |
| authorships[0].is_corresponding | True |
| authorships[1].author.id | https://openalex.org/A2260895292 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Liang Jin-hua |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Liang, Jinhua |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A1965012384 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Zhang Huan |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Zhang, Huan |
| authorships[2].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.5281/zenodo.17488857 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-11-05T00:00:00 |
| display_name | Hierarchical Symbolic Pop Music Generation with Graph Neural Networks |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11349 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.5400663614273071 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1707 |
| primary_topic.subfield.display_name | Computer Vision and Pattern Recognition |
| primary_topic.display_name | Music Technology and Sound Studies |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.5281/zenodo.17488857 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400562 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Zenodo (CERN European Organization for Nuclear Research) |
| best_oa_location.source.host_organization | https://openalex.org/I67311998 |
| best_oa_location.source.host_organization_name | European Organization for Nuclear Research |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I67311998 |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | |
| best_oa_location.version | |
| best_oa_location.raw_type | |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | https://doi.org/10.5281/zenodo.17488857 |
| primary_location.id | doi:10.5281/zenodo.17488857 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400562 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Zenodo (CERN European Organization for Nuclear Research) |
| primary_location.source.host_organization | https://openalex.org/I67311998 |
| primary_location.source.host_organization_name | European Organization for Nuclear Research |
| primary_location.source.host_organization_lineage | https://openalex.org/I67311998 |
| primary_location.license | cc-by |
| primary_location.pdf_url | |
| primary_location.version | |
| primary_location.raw_type | |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://doi.org/10.5281/zenodo.17488857 |
| publication_date | 2025-11-03 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 65, 84, 107 |
| abstract_inverted_index.In | 60 |
| abstract_inverted_index.We | 99 |
| abstract_inverted_index.as | 11 |
| abstract_inverted_index.do | 54 |
| abstract_inverted_index.in | 140 |
| abstract_inverted_index.is | 1, 36 |
| abstract_inverted_index.of | 5, 18, 77, 136 |
| abstract_inverted_index.on | 32, 44, 106, 116 |
| abstract_inverted_index.to | 14, 50, 68, 89, 110, 120, 133 |
| abstract_inverted_index.up | 4 |
| abstract_inverted_index.we | 63, 82 |
| abstract_inverted_index.Our | 125 |
| abstract_inverted_index.and | 8, 47, 74, 96, 114, 146, 150 |
| abstract_inverted_index.are | 131 |
| abstract_inverted_index.for | 57 |
| abstract_inverted_index.has | 23 |
| abstract_inverted_index.not | 55 |
| abstract_inverted_index.one | 105 |
| abstract_inverted_index.pop | 79 |
| abstract_inverted_index.the | 71, 129, 137, 141 |
| abstract_inverted_index.two | 101 |
| abstract_inverted_index.MIDI | 108 |
| abstract_inverted_index.able | 132 |
| abstract_inverted_index.aims | 88 |
| abstract_inverted_index.been | 24 |
| abstract_inverted_index.both | 70 |
| abstract_inverted_index.deep | 28 |
| abstract_inverted_index.full | 122 |
| abstract_inverted_index.made | 3 |
| abstract_inverted_index.most | 135 |
| abstract_inverted_index.only | 43 |
| abstract_inverted_index.song | 117, 123 |
| abstract_inverted_index.that | 87, 128 |
| abstract_inverted_index.them | 10 |
| abstract_inverted_index.this | 61 |
| abstract_inverted_index.with | 93 |
| abstract_inverted_index.work | 126 |
| abstract_inverted_index.4-bar | 112 |
| abstract_inverted_index.Music | 0 |
| abstract_inverted_index.While | 20 |
| abstract_inverted_index.chord | 145 |
| abstract_inverted_index.helps | 13 |
| abstract_inverted_index.learn | 134 |
| abstract_inverted_index.music | 21, 34, 40, 53, 92 |
| abstract_inverted_index.pitch | 147 |
| abstract_inverted_index.shows | 127 |
| abstract_inverted_index.train | 100 |
| abstract_inverted_index.using | 26 |
| abstract_inverted_index.works | 49 |
| abstract_inverted_index.graphs | 12 |
| abstract_inverted_index.labels | 119 |
| abstract_inverted_index.levels | 17 |
| abstract_inverted_index.models | 130 |
| abstract_inverted_index.music. | 80 |
| abstract_inverted_index.paper, | 62 |
| abstract_inverted_index.phrase | 75, 151 |
| abstract_inverted_index.recent | 48 |
| abstract_inverted_index.rhythm | 95 |
| abstract_inverted_index.worked | 42 |
| abstract_inverted_index.Chinese | 78 |
| abstract_inverted_index.Earlier | 38 |
| abstract_inverted_index.account | 56 |
| abstract_inverted_index.another | 115 |
| abstract_inverted_index.capture | 15 |
| abstract_inverted_index.complex | 6 |
| abstract_inverted_index.dataset | 109 |
| abstract_inverted_index.explore | 64 |
| abstract_inverted_index.nuances | 139 |
| abstract_inverted_index.propose | 83 |
| abstract_inverted_index.sparse. | 37 |
| abstract_inverted_index.various | 27 |
| abstract_inverted_index.approach | 67, 86 |
| abstract_inverted_index.coherent | 94 |
| abstract_inverted_index.dataset, | 143 |
| abstract_inverted_index.explored | 25 |
| abstract_inverted_index.generate | 51, 90, 111, 121 |
| abstract_inverted_index.multiple | 16 |
| abstract_inverted_index.patterns | 73 |
| abstract_inverted_index.phrases, | 113 |
| abstract_inverted_index.research | 31 |
| abstract_inverted_index.rhythmic | 72 |
| abstract_inverted_index.training | 142 |
| abstract_inverted_index.two-step | 85 |
| abstract_inverted_index.frequency | 148 |
| abstract_inverted_index.including | 144 |
| abstract_inverted_index.long-term | 97 |
| abstract_inverted_index.melodies, | 46 |
| abstract_inverted_index.networks: | 104 |
| abstract_inverted_index.represent | 69 |
| abstract_inverted_index.structure | 76, 118 |
| abstract_inverted_index.generating | 45 |
| abstract_inverted_index.generation | 22, 29, 35, 41 |
| abstract_inverted_index.inherently | 2 |
| abstract_inverted_index.polyphonic | 52, 91 |
| abstract_inverted_index.structural | 138 |
| abstract_inverted_index.structure. | 59, 98, 124 |
| abstract_inverted_index.Variational | 102 |
| abstract_inverted_index.attributes. | 152 |
| abstract_inverted_index.graph-based | 39 |
| abstract_inverted_index.longer-term | 58 |
| abstract_inverted_index.multi-graph | 66 |
| abstract_inverted_index.structures, | 7 |
| abstract_inverted_index.techniques, | 30 |
| abstract_inverted_index.Auto-Encoder | 103 |
| abstract_inverted_index.representing | 9 |
| abstract_inverted_index.Consequently, | 81 |
| abstract_inverted_index.graph-related | 33 |
| abstract_inverted_index.distributions, | 149 |
| abstract_inverted_index.relationships. | 19 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile.value | 0.795767 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |