{"id":"https://openalex.org/W4408347256","doi":"https://doi.org/10.1109/icassp49660.2025.10889579","title":"D3RM: A Discrete Denoising Diffusion Refinement Model for Piano Transcription","display_name":"D3RM: A Discrete Denoising Diffusion Refinement Model for Piano Transcription","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408347256","doi":"https://doi.org/10.1109/icassp49660.2025.10889579"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889579","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":["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/A5033570183","display_name":"Hounsu Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hounsu Kim","raw_affiliation_strings":["Graduate School of Culture Technology KAIST,Daejeon,South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Culture Technology KAIST,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115444778","display_name":"Taegyun Kwon","orcid":"https://orcid.org/0009-0004-8510-872X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taegyun Kwon","raw_affiliation_strings":["Graduate School of Culture Technology KAIST,Daejeon,South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Culture Technology KAIST,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056437111","display_name":"Juhan Nam","orcid":"https://orcid.org/0000-0003-2664-2119"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhan Nam","raw_affiliation_strings":["Graduate School of Culture Technology KAIST,Daejeon,South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Culture Technology KAIST,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033570183"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04928989,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/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/T13996","display_name":"Diverse Musicological Studies","score":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.7322499752044678},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5695948004722595},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5457711219787598},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4408806264400482},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.43931272625923157},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43817633390426636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28102391958236694},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1796148717403412},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12201821804046631}],"concepts":[{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.7322499752044678},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5695948004722595},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5457711219787598},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4408806264400482},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.43931272625923157},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43817633390426636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28102391958236694},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1796148717403412},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12201821804046631},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889579","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W3209419355","https://openalex.org/W4312388283","https://openalex.org/W4367359628","https://openalex.org/W4375869480","https://openalex.org/W4386075553","https://openalex.org/W4392910816","https://openalex.org/W4404788072","https://openalex.org/W6679045638","https://openalex.org/W6714030504","https://openalex.org/W6745851314","https://openalex.org/W6755182157","https://openalex.org/W6783182287","https://openalex.org/W6784081880","https://openalex.org/W6796163713","https://openalex.org/W6798447524","https://openalex.org/W6798855526","https://openalex.org/W6844872470","https://openalex.org/W6846575651","https://openalex.org/W6853498704","https://openalex.org/W6854061045","https://openalex.org/W6862144568","https://openalex.org/W6864687309"],"related_works":["https://openalex.org/W2316271602","https://openalex.org/W2357375963","https://openalex.org/W607893370","https://openalex.org/W629160228","https://openalex.org/W584653787","https://openalex.org/W4362512397","https://openalex.org/W587444722","https://openalex.org/W2022713566","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"Diffusion":[0],"models":[1,35,136],"have":[2,22,36],"been":[3,38],"widely":[4],"used":[5],"in":[6,15,141],"the":[7,79,84,91,124,138,151],"generative":[8],"domain":[9],"due":[10],"to":[11,48],"their":[12,44],"convincing":[13],"performance":[14,45],"modeling":[16],"complex":[17],"data":[18],"distributions.":[19],"Moreover,":[20],"they":[21],"shown":[23],"competitive":[24,51],"results":[25],"on":[26,58,90,123,150],"discriminative":[27],"tasks,":[28],"such":[29],"as":[30,78],"image":[31],"segmentation.":[32],"While":[33],"diffusion":[34,60,120],"also":[37],"explored":[39],"for":[40,69],"automatic":[41],"music":[42],"transcription,":[43],"has":[46],"yet":[47],"reach":[49],"a":[50,66,95,105],"level.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56,103],"focus":[57],"discrete":[59,119],"model\u2019s":[61],"refinement":[62],"capabilities":[63],"and":[64,115,137],"present":[65],"novel":[67,106],"architecture":[68],"piano":[70,87,134],"transcription.":[71],"Our":[72,146],"model":[73,140],"utilizes":[74],"Neighborhood":[75],"Attention":[76],"layers":[77],"denoising":[80],"module,":[81],"gradually":[82],"predicting":[83],"target":[85],"high-resolution":[86],"roll,":[88],"conditioned":[89],"finetuned":[92],"features":[93],"of":[94,118,143],"pretrained":[96],"acoustic":[97],"model.":[98],"To":[99],"further":[100],"enhance":[101],"refinement,":[102],"devise":[104],"strategy":[107],"which":[108],"applies":[109],"distinct":[110],"transition":[111],"states":[112],"during":[113],"training":[114],"inference":[116],"stage":[117],"models.":[121],"Experiments":[122],"MAESTRO":[125],"dataset":[126],"show":[127],"that":[128],"our":[129],"approach":[130],"outperforms":[131],"previous":[132],"diffusion-based":[133],"transcription":[135],"baseline":[139],"terms":[142],"F1":[144],"score.":[145],"code":[147],"is":[148],"available":[149],"accompanying":[152],"website":[153],"<sup":[154],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[155],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[156]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}