{"id":"https://openalex.org/W4386763510","doi":"https://doi.org/10.1109/waspaa58266.2023.10248148","title":"All-in-One Metrical and Functional Structure Analysis with Neighborhood Attentions on Demixed Audio","display_name":"All-in-One Metrical and Functional Structure Analysis with Neighborhood Attentions on Demixed Audio","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386763510","doi":"https://doi.org/10.1109/waspaa58266.2023.10248148"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa58266.2023.10248148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5113001529","display_name":"Taejun 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":"Taejun Kim","raw_affiliation_strings":["Graduate School of Culture Technology,KAIST,Daejeon,Republic of Korea","KAIST, Graduate School of Culture Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Culture Technology,KAIST,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"KAIST, Graduate School of Culture Technology, Daejeon, Republic of 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,Republic of Korea","KAIST, Graduate School of Culture Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Culture Technology,KAIST,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"KAIST, Graduate School of Culture Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113001529"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":2.4399,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.9007323,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"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":1.0,"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":1.0,"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":0.9991000294685364,"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":0.9980000257492065,"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/spectrogram","display_name":"Spectrogram","score":0.8328292369842529},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7953002452850342},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6143684387207031},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5170760154724121},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48747682571411133},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4753149151802063},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.41696518659591675},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3343786597251892},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32636725902557373}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8328292369842529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7953002452850342},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6143684387207031},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5170760154724121},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48747682571411133},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4753149151802063},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.41696518659591675},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3343786597251892},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32636725902557373},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa58266.2023.10248148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323890","display_name":"Korea Creative Content Agency","ror":"https://ror.org/036vyg793"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2053049659","https://openalex.org/W2168249484","https://openalex.org/W2404298818","https://openalex.org/W2404620398","https://openalex.org/W2405656250","https://openalex.org/W2572771584","https://openalex.org/W2792764867","https://openalex.org/W2939753704","https://openalex.org/W2939929812","https://openalex.org/W2963173418","https://openalex.org/W2968917279","https://openalex.org/W2984379537","https://openalex.org/W2989608619","https://openalex.org/W2990861008","https://openalex.org/W3112091658","https://openalex.org/W3118825798","https://openalex.org/W3162686331","https://openalex.org/W3207313418","https://openalex.org/W3214581616","https://openalex.org/W4224918587","https://openalex.org/W4224944643","https://openalex.org/W4297847268","https://openalex.org/W4298187611","https://openalex.org/W4309501294","https://openalex.org/W4372260250","https://openalex.org/W4386075553","https://openalex.org/W6712946787","https://openalex.org/W6713195707","https://openalex.org/W6749107692","https://openalex.org/W6749825310","https://openalex.org/W6767164110","https://openalex.org/W6770646036","https://openalex.org/W6784730479","https://openalex.org/W6803325066","https://openalex.org/W6804109046","https://openalex.org/W6844051892","https://openalex.org/W6844204944","https://openalex.org/W6846277122","https://openalex.org/W6941176339"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W2011227383","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W2065606036","https://openalex.org/W3179495260","https://openalex.org/W3127543252","https://openalex.org/W4386392971"],"abstract_inverted_index":{"Music":[0,24],"is":[1],"characterized":[2],"by":[3],"complex":[4],"hierarchical":[5,39],"structures.":[6],"Developing":[7],"a":[8,17,44,52,113],"comprehensive":[9],"model":[10,55,72,99],"to":[11,83,120,140],"capture":[12,84],"these":[13],"structures":[14],"has":[15,30],"been":[16],"significant":[18],"challenge":[19],"in":[20,103],"the":[21,97,108,130,149],"field":[22],"of":[23,117,133],"Information":[25],"Retrieval":[26],"(MIR).":[27],"Prior":[28],"research":[29],"mainly":[31],"focused":[32],"on":[33,107],"addressing":[34],"individual":[35],"tasks":[36,106],"for":[37,92],"specific":[38],"levels,":[40],"rather":[41],"than":[42],"providing":[43],"unified":[45],"approach.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50],"introduce":[51],"versatile,":[53],"all-in-one":[54],"that":[56,129],"jointly":[57],"performs":[58],"beat":[59],"and":[60,69,78,136],"downbeat":[61],"tracking":[62],"as":[63,65,76],"well":[64],"functional":[66],"structure":[67],"segmentation":[68],"labeling.":[70],"The":[71],"leverages":[73],"source-separated":[74],"spectrograms":[75],"inputs":[77],"employs":[79],"dilated":[80],"neighborhood":[81],"attentions":[82,91],"temporal":[85],"long-term":[86],"dependencies,":[87],"along":[88],"with":[89,143],"non-dilated":[90],"local":[93],"instrumental":[94],"dependencies.":[95],"Consequently,":[96],"proposed":[98],"achieves":[100],"state-of-the-art":[101,122],"performance":[102],"all":[104],"four":[105],"Harmonix":[109],"Set":[110],"while":[111],"maintaining":[112],"relatively":[114],"lower":[115],"number":[116],"parameters":[118],"compared":[119],"recent":[121],"models.":[123],"Furthermore,":[124],"our":[125],"ablation":[126],"study":[127],"demonstrates":[128],"concurrent":[131],"learning":[132],"beats,":[134],"downbeats,":[135],"segments":[137],"can":[138],"lead":[139],"enhanced":[141],"performance,":[142],"each":[144],"task":[145],"mutually":[146],"benefiting":[147],"from":[148],"others.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}