{"id":"https://openalex.org/W4392077356","doi":"https://doi.org/10.1109/icassp48485.2024.10448149","title":"Structure-Informed Positional Encoding for Music Generation","display_name":"Structure-Informed Positional Encoding for Music Generation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392077356","doi":"https://doi.org/10.1109/icassp48485.2024.10448149"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448149","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2402.13301","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103581717","display_name":"Manvi Agarwal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Manvi Agarwal","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com Paris,France"],"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I4210145102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427145","display_name":"Changhong Wang","orcid":"https://orcid.org/0000-0003-2821-9357"},"institutions":[{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Changhong Wang","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com Paris,France"],"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I4210145102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055423112","display_name":"Ga\u00ebl Richard","orcid":"https://orcid.org/0000-0002-4960-0010"},"institutions":[{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ga\u00ebl Richard","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com Paris,France"],"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I4210145102"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103581717"],"corresponding_institution_ids":["https://openalex.org/I4210145102","https://openalex.org/I4210165912"],"apc_list":null,"apc_paid":null,"fwci":0.7312,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68587122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"951","last_page":"955"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.967199981212616,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.832990825176239},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8018996119499207},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.643602728843689},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5691708326339722},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5200616717338562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4916449189186096},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4878666400909424},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4239887595176697},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3514930009841919},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.328784704208374},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08309602737426758}],"concepts":[{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.832990825176239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8018996119499207},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.643602728843689},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5691708326339722},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5200616717338562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4916449189186096},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4878666400909424},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4239887595176697},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3514930009841919},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.328784704208374},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08309602737426758},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448149","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2402.13301","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.13301","pdf_url":"https://arxiv.org/pdf/2402.13301","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:HAL:hal-04432659v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04432659","pdf_url":"https://hal.science/hal-04432659/document","source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:HAL:hal-04432659v3","is_oa":true,"landing_page_url":"https://hal.science/hal-04432659v3/document","pdf_url":"https://hal.science/hal-04432659v3/file/svbwdvrdnrztpzxgdsckkhqxkjbjpfzx.pdf","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2024, Seoul, South Korea. &#x27E8;10.1109/ICASSP48485.2024.10448149&#x27E9;","raw_type":"Conference papers"},{"id":"pmh:oai:zenodo.org:10932363","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ICASSP48485.2024.10448149","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},{"id":"doi:10.48550/arxiv.2402.13301","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.13301","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2402.13301","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.13301","pdf_url":"https://arxiv.org/pdf/2402.13301","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392077356.pdf"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1567012231","https://openalex.org/W2296073425","https://openalex.org/W2919624000","https://openalex.org/W2921317107","https://openalex.org/W2963925437","https://openalex.org/W2983902802","https://openalex.org/W3047325651","https://openalex.org/W3049247973","https://openalex.org/W3085139254","https://openalex.org/W3092879656","https://openalex.org/W3163721282","https://openalex.org/W3163784447","https://openalex.org/W3170209909","https://openalex.org/W3175663427","https://openalex.org/W3199404008","https://openalex.org/W4280589076","https://openalex.org/W4287688462","https://openalex.org/W4297849347","https://openalex.org/W4319323855","https://openalex.org/W4377140494","https://openalex.org/W4379087247","https://openalex.org/W4382239517","https://openalex.org/W4385245566","https://openalex.org/W4385573607","https://openalex.org/W6634150524","https://openalex.org/W6739901393","https://openalex.org/W6760601182","https://openalex.org/W6781678156","https://openalex.org/W6781910838","https://openalex.org/W6782590614","https://openalex.org/W6783267081","https://openalex.org/W6784760813","https://openalex.org/W6795453751","https://openalex.org/W6795818498","https://openalex.org/W6796022967","https://openalex.org/W6838053213","https://openalex.org/W6843687776","https://openalex.org/W6849617516","https://openalex.org/W6853205265","https://openalex.org/W6861797540"],"related_works":["https://openalex.org/W1908769745","https://openalex.org/W2144131839","https://openalex.org/W2039049596","https://openalex.org/W3012755723","https://openalex.org/W4243499289","https://openalex.org/W2092287538","https://openalex.org/W2291136386","https://openalex.org/W2023541445","https://openalex.org/W1597258651","https://openalex.org/W2162924463"],"abstract_inverted_index":{"Music":[0],"generated":[1,105],"by":[2],"deep":[3],"learning":[4],"methods":[5,87,96],"often":[6],"suffers":[7],"from":[8,78],"a":[9,21,33,72],"lack":[10],"of":[11,24,49,85,103],"coherence":[12],"and":[13,52,68,81,100],"long-term":[14],"organization.":[15],"Yet,":[16],"multi-scale":[17],"hierarchical":[18],"structure":[19],"is":[20],"distinctive":[22],"feature":[23],"music":[25,39,63],"signals.":[26],"To":[27],"leverage":[28],"this":[29],"information,":[30],"we":[31,74],"propose":[32],"structure-informed":[34],"positional":[35,54],"encoding":[36],"framework":[37],"for":[38],"generation":[40,64],"with":[41],"Transformers.":[42],"We":[43,56],"design":[44],"three":[45],"variants":[46],"in":[47],"terms":[48],"absolute,":[50],"relative":[51],"non-stationary":[53],"information.":[55],"comprehensively":[57],"test":[58],"them":[59],"on":[60],"two":[61],"symbolic":[62],"tasks:":[65],"next-timestep":[66],"prediction":[67],"accompaniment":[69],"generation.":[70],"As":[71],"comparison,":[73],"choose":[75],"multiple":[76],"baselines":[77],"the":[79,83,98,104],"literature":[80],"demonstrate":[82],"merits":[84],"our":[86,95],"using":[88],"several":[89],"musically-motivated":[90],"evaluation":[91],"metrics.":[92],"In":[93],"particular,":[94],"improve":[97],"melodic":[99],"structural":[101],"consistency":[102],"pieces.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2024-02-23T00:00:00"}
