{"id":"https://openalex.org/W4408352559","doi":"https://doi.org/10.1109/icassp49660.2025.10890396","title":"No Data Required: Zero-Shot Domain Adaptation for Automatic Music Transcription","display_name":"No Data Required: Zero-Shot Domain Adaptation for Automatic Music Transcription","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352559","doi":"https://doi.org/10.1109/icassp49660.2025.10890396"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890396","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002469859","display_name":"Andrew McLeod","orcid":"https://orcid.org/0000-0003-2700-2076"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Andrew McLeod","raw_affiliation_strings":["Fraunhofer IDMT,Semantic Music Technologies,Ilmenau,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT,Semantic Music Technologies,Ilmenau,Germany","institution_ids":["https://openalex.org/I4210138578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5002469859"],"corresponding_institution_ids":["https://openalex.org/I4210138578"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10515","display_name":"Cancer-related molecular mechanisms research","score":0.9519000053405762,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6853256225585938},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6443119049072266},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.47848719358444214},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44821423292160034},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4361097812652588},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39771682024002075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27716049551963806},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12896963953971863},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.08402252197265625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6853256225585938},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6443119049072266},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.47848719358444214},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44821423292160034},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4361097812652588},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39771682024002075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27716049551963806},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12896963953971863},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.08402252197265625},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890396","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:publica.fraunhofer.de:publica/486541","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/486541","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2066334462","https://openalex.org/W3045884425","https://openalex.org/W3206146520","https://openalex.org/W3209419355","https://openalex.org/W4386696315","https://openalex.org/W4388118708","https://openalex.org/W4391640266","https://openalex.org/W4392903082","https://openalex.org/W4392909613","https://openalex.org/W6714030504","https://openalex.org/W6731203071","https://openalex.org/W6745851314","https://openalex.org/W6755182157","https://openalex.org/W6756341328","https://openalex.org/W6798855526","https://openalex.org/W6803088475","https://openalex.org/W6803227292","https://openalex.org/W6810809420","https://openalex.org/W6846720292","https://openalex.org/W6856125517"],"related_works":["https://openalex.org/W4389474468","https://openalex.org/W4300172004","https://openalex.org/W2028097510","https://openalex.org/W2505877856","https://openalex.org/W3203792196","https://openalex.org/W4321649381","https://openalex.org/W2997645659","https://openalex.org/W3180787869","https://openalex.org/W2955455867","https://openalex.org/W4295929828"],"abstract_inverted_index":{"Automatic":[0],"music":[1,6],"transcription":[2,11,83,140],"(AMT)":[3],"takes":[4],"a":[5,10,77,81,134],"recording":[7,149,155],"and":[8,64,85,141,157,161,172],"outputs":[9],"of":[12,26,69,104,117],"the":[13,67,93,105,111,121,127],"underlying":[14],"music.":[15,42],"Deep":[16],"learning":[17],"models":[18,45],"trained":[19,137],"for":[20,34,79,95,138],"AMT":[21],"rely":[22],"on":[23,46,58,66,89],"large":[24],"amounts":[25],"annotated":[27],"training":[28,97],"data,":[29,98],"which":[30],"are":[31],"available":[32],"only":[33],"some":[35],"domains":[36,61],"such":[37],"as":[38],"Western":[39],"classical":[40],"piano":[41,139],"Using":[43],"pre-trained":[44,82],"out-of-domain":[47,90],"inputs":[48],"can":[49],"lead":[50],"to":[51,113],"significantly":[52],"lower":[53],"performance.":[54,174],"Fine-tuning":[55],"or":[56,102],"retraining":[57,103],"new":[59],"target":[60],"is":[62,130],"expensive":[63],"relies":[65],"presence":[68],"labeled":[70],"data.":[71],"In":[72],"this":[73],"work,":[74],"we":[75],"propose":[76],"method":[78,109,168],"taking":[80],"model":[84,112,129,135],"improving":[86],"its":[87],"performance":[88],"data":[91],"without":[92],"need":[94],"any":[96],"requiring":[99],"no":[100],"fine-tuning":[101],"original":[106,128],"model.":[107],"Our":[108],"uses":[110],"transcribe":[114],"pitch-shifted":[115],"versions":[116,125],"an":[118],"input,":[119],"aggregating":[120],"output":[122],"across":[123],"these":[124],"where":[126],"unsure.":[131],"We":[132,164],"take":[133],"originally":[136],"present":[142],"experiments":[143],"under":[144],"two":[145],"domain":[146],"shift":[147],"scenarios:":[148],"condition":[150],"mismatch":[151,159],"(piano":[152],"with":[153],"different":[154],"setups)":[156],"instrument":[158],"(guitar":[160],"choral":[162],"data).":[163],"show":[165],"that":[166],"our":[167],"consistently":[169],"improves":[170],"note-":[171],"frame-based":[173]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
