{"id":"https://openalex.org/W4375869026","doi":"https://doi.org/10.1109/icassp49357.2023.10095769","title":"MAID: A Conditional Diffusion Model for Long Music Audio Inpainting","display_name":"MAID: A Conditional Diffusion Model for Long Music Audio Inpainting","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869026","doi":"https://doi.org/10.1109/icassp49357.2023.10095769"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5024284822","display_name":"Kaiyang Liu","orcid":"https://orcid.org/0000-0002-1114-8030"},"institutions":[{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]},{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kaiyang Liu","raw_affiliation_strings":["Sichuan University,College of Computer Science,Chengdu,China","College of Computer Science, Sichuan University, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Computer Science,Chengdu,China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]},{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020922543","display_name":"Wendong Gan","orcid":null},"institutions":[{"id":"https://openalex.org/I882086362","display_name":"Wipro (Singapore)","ror":"https://ror.org/01hbz8t53","country_code":"SG","type":"company","lineage":["https://openalex.org/I4210090636","https://openalex.org/I882086362"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wendong Gan","raw_affiliation_strings":["Wiz Holdings Pte Ltd,Singapore","Wiz Holdings Pte Ltd, Singapore"],"affiliations":[{"raw_affiliation_string":"Wiz Holdings Pte Ltd,Singapore","institution_ids":["https://openalex.org/I882086362"]},{"raw_affiliation_string":"Wiz Holdings Pte Ltd, Singapore","institution_ids":["https://openalex.org/I882086362"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016097084","display_name":"Chenchen Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenchen Yuan","raw_affiliation_strings":["Sichuan University,College of Computer Science,Chengdu,China","College of Computer Science, Sichuan University, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Computer Science,Chengdu,China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]},{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024284822"],"corresponding_institution_ids":["https://openalex.org/I24185976","https://openalex.org/I4210125143"],"apc_list":null,"apc_paid":null,"fwci":1.4473,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81908127,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"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":0.9998000264167786,"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":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9965999722480774,"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":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.9665889739990234},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6101037263870239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5151458978652954},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49325650930404663},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47028234601020813},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.35791152715682983},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3367413878440857},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08610311150550842}],"concepts":[{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.9665889739990234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6101037263870239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5151458978652954},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49325650930404663},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47028234601020813},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.35791152715682983},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3367413878440857},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08610311150550842},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2129069237","https://openalex.org/W2133665775","https://openalex.org/W2296153915","https://openalex.org/W2516594951","https://openalex.org/W2559688696","https://openalex.org/W2898371500","https://openalex.org/W2899000566","https://openalex.org/W2950547518","https://openalex.org/W2963276790","https://openalex.org/W2981905048","https://openalex.org/W2985518820","https://openalex.org/W2999782137","https://openalex.org/W3012382391","https://openalex.org/W3022195800","https://openalex.org/W3036167779","https://openalex.org/W3103301587","https://openalex.org/W3105000799","https://openalex.org/W3105183525","https://openalex.org/W3110257065","https://openalex.org/W3129651364","https://openalex.org/W3162926177","https://openalex.org/W3215331646","https://openalex.org/W4224035735","https://openalex.org/W4283697979","https://openalex.org/W4296068407","https://openalex.org/W4313680291","https://openalex.org/W6639824700","https://openalex.org/W6730401039","https://openalex.org/W6755182157","https://openalex.org/W6769995984","https://openalex.org/W6775691539","https://openalex.org/W6779823529","https://openalex.org/W6783182287","https://openalex.org/W6786375611","https://openalex.org/W6795288823","https://openalex.org/W6809885388"],"related_works":["https://openalex.org/W3178025616","https://openalex.org/W2060947339","https://openalex.org/W2131831293","https://openalex.org/W2017457812","https://openalex.org/W1995073329","https://openalex.org/W2946160871","https://openalex.org/W3035059915","https://openalex.org/W425542480","https://openalex.org/W49967185","https://openalex.org/W2107727507"],"abstract_inverted_index":{"Recent":[0],"works":[1],"on":[2,9,49,106],"long":[3],"music":[4,45,65],"audio":[5,17,46],"inpainting":[6,47,63,71,77,92],"have":[7],"focused":[8],"unconditionally":[10],"generating":[11],"new":[12,98],"segments":[13,24,99,104],"to":[14,101,110],"inpaint":[15],"corrupted":[16],"segments.":[18],"However,":[19],"the":[20,29,69,90,94,102,107,111,120],"information":[21],"about":[22],"these":[23],"may":[25],"differ":[26],"significantly":[27],"from":[28],"original.":[30],"To":[31],"solve":[32],"this":[33],"problem,":[34],"we":[35],"propose":[36],"MAID":[37,73,116],"(Music":[38],"Audio":[39],"Inpainting":[40],"DDPM),":[41],"a":[42,80],"model":[43,56,95],"for":[44],"based":[48,105],"DDPM":[50],"(Denoising":[51],"Diffusion":[52],"Probability":[53],"Model).":[54],"The":[55],"is":[57,74],"capable":[58,75],"of":[59,64,76],"unconditional":[60,70],"and":[61,85],"conditional":[62,91],"audio:":[66],"(a)":[67],"in":[68,89],"task,":[72,93],"gaps":[78],"with":[79],"length":[81],"between":[82],"200":[83],"ms":[84],"1600":[86],"ms;":[87],"(b)":[88],"can":[96],"generate":[97],"similar":[100],"original":[103],"piano-rolls":[108],"corresponding":[109],"gaps.":[112],"Experiments":[113],"show":[114],"that":[115],"performs":[117],"better":[118],"than":[119],"baseline.":[121]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}