{"id":"https://openalex.org/W4407559316","doi":"https://doi.org/10.1109/icassp49660.2025.10888904","title":"F-StrIPE: Fast Structure-Informed Positional Encoding for Symbolic Music Generation","display_name":"F-StrIPE: Fast Structure-Informed Positional Encoding for Symbolic Music Generation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4407559316","doi":"https://doi.org/10.1109/icassp49660.2025.10888904"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.10491","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/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"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, Télécom Paris,France","IDS - D\u00e9partement Images, Donn\u00e9es, Signal (46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019) - France)","T\u00e9l\u00e9com Paris (19 Place Marguerite Perey 91120 Palaiseau - France)","IP Paris - Institut Polytechnique de Paris (Route de Saclay, 91120 Palaiseau Cedex, France - France)","LTCI - Laboratoire Traitement et Communication de l'Information (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 PALAISEAU - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, Télécom Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I4210145102"]},{"raw_affiliation_string":"IDS - D\u00e9partement Images, Donn\u00e9es, Signal (46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019) - France)","institution_ids":[]},{"raw_affiliation_string":"T\u00e9l\u00e9com Paris (19 Place Marguerite Perey 91120 Palaiseau - France)","institution_ids":["https://openalex.org/I12356871"]},{"raw_affiliation_string":"IP Paris - Institut Polytechnique de Paris (Route de Saclay, 91120 Palaiseau Cedex, France - France)","institution_ids":["https://openalex.org/I4210145102"]},{"raw_affiliation_string":"LTCI - Laboratoire Traitement et Communication de l'Information (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 PALAISEAU - France)","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]}]},{"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/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"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, Télécom Paris,France","LTCI - Telecom-Paris, Institut Polytechnique de Paris (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, Télécom Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I4210145102"]},{"raw_affiliation_string":"LTCI - Telecom-Paris, Institut Polytechnique de Paris (France)","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113927018","display_name":"Ga\u00ebl Richard","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"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, Télécom Paris,France","S2A - Signal, Statistique et Apprentissage (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 Palaiseau - France)","IDS - D\u00e9partement Images, Donn\u00e9es, Signal (46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019) - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, Télécom Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I4210145102"]},{"raw_affiliation_string":"S2A - Signal, Statistique et Apprentissage (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 Palaiseau - France)","institution_ids":["https://openalex.org/I12356871"]},{"raw_affiliation_string":"IDS - D\u00e9partement Images, Donn\u00e9es, Signal (46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019) - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103581717"],"corresponding_institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210145102","https://openalex.org/I4210165912"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01622921,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9972000122070312,"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":0.9972000122070312,"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":0.9955999851226807,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9743000268936157,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6833916306495667},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.589472234249115},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5041793584823608},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.48636963963508606},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.47844648361206055},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.46480146050453186},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.46073055267333984},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.45716726779937744},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4325127601623535},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4273955523967743},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41547057032585144},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4084557890892029},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20504334568977356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6833916306495667},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.589472234249115},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5041793584823608},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.48636963963508606},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.47844648361206055},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.46480146050453186},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.46073055267333984},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.45716726779937744},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4325127601623535},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4273955523967743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41547057032585144},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4084557890892029},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20504334568977356},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.10491","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.10491","pdf_url":"https://arxiv.org/pdf/2502.10491","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-04935674v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04935674","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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 2025, Hyderabad, India","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.10491","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.10491","pdf_url":"https://arxiv.org/pdf/2502.10491","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407559316.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2296073425","https://openalex.org/W2557876557","https://openalex.org/W2809621972","https://openalex.org/W2963925437","https://openalex.org/W2983902802","https://openalex.org/W3085139254","https://openalex.org/W3092850823","https://openalex.org/W3120633509","https://openalex.org/W4377140494","https://openalex.org/W4377719641","https://openalex.org/W4382239517","https://openalex.org/W4385573607","https://openalex.org/W4392077356","https://openalex.org/W4395093993","https://openalex.org/W4405974183","https://openalex.org/W6616109796","https://openalex.org/W6681302627","https://openalex.org/W6682743674","https://openalex.org/W6739901393","https://openalex.org/W6772383348","https://openalex.org/W6779709467","https://openalex.org/W6781678156","https://openalex.org/W6781910838","https://openalex.org/W6783944145","https://openalex.org/W6784760813","https://openalex.org/W6795453751","https://openalex.org/W6838053213","https://openalex.org/W6842644747","https://openalex.org/W6843687776"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W323006901","https://openalex.org/W3014948380","https://openalex.org/W2129146436","https://openalex.org/W2032507829","https://openalex.org/W4391584540","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424"],"abstract_inverted_index":{"While":[0],"music":[1],"remains":[2],"a":[3,44,56,79],"challenging":[4],"domain":[5],"for":[6,96],"generative":[7],"models":[8],"like":[9],"Transformers,":[10],"recent":[11],"progress":[12],"has":[13],"been":[14],"made":[15],"by":[16],"exploiting":[17],"suitable":[18],"musically-informed":[19],"priors.":[20],"One":[21],"technique":[22],"to":[23],"leverage":[24],"information":[25],"about":[26],"musical":[27],"structure":[28],"in":[29,47,62],"Transformers":[30,42],"is":[31,78],"inserting":[32],"such":[33],"knowledge":[34],"into":[35],"the":[36,88],"positional":[37],"encoding":[38],"(PE)":[39],"module.":[40],"However,":[41],"carry":[43],"quadratic":[45],"cost":[46],"sequence":[48],"length.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,74],"propose":[54],"F-StrIPE,":[55],"structure-informed":[57],"PE":[58],"scheme":[59],"that":[60,76],"works":[61],"linear":[63],"complexity.":[64],"Using":[65],"existing":[66],"kernel":[67],"approximation":[68],"techniques":[69],"based":[70],"on":[71],"random":[72],"features,":[73],"show":[75],"F-StrIPE":[77,92],"generalization":[80],"of":[81,91],"Stochastic":[82],"Positional":[83],"Encoding":[84],"(SPE).":[85],"We":[86],"illustrate":[87],"empirical":[89],"merits":[90],"using":[93],"melody":[94],"harmonization":[95],"symbolic":[97],"music.":[98]},"counts_by_year":[],"updated_date":"2026-06-01T08:46:32.239190","created_date":"2025-10-10T00:00:00"}