{"id":"https://openalex.org/W3112098675","doi":"https://doi.org/10.1109/taslp.2020.3030484","title":"Hierarchical Regulated Iterative Network for Joint Task of Music Detection and Music Relative Loudness Estimation","display_name":"Hierarchical Regulated Iterative Network for Joint Task of Music Detection and Music Relative Loudness Estimation","publication_year":2020,"publication_date":"2020-10-13","ids":{"openalex":"https://openalex.org/W3112098675","doi":"https://doi.org/10.1109/taslp.2020.3030484","mag":"3112098675"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3030484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3030484","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5071448327","display_name":"Bijue Jia","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/I4391767678","display_name":"State Key Laboratory of Hydraulics and Mountain River Engineering","ror":"https://ror.org/02169wb20","country_code":null,"type":"facility","lineage":["https://openalex.org/I24185976","https://openalex.org/I4391767678"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bijue Jia","raw_affiliation_strings":["College of Computer Science, State Key Laboratory of Hydraulics and Mountain River Engineering, Sichuan University, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, State Key Laboratory of Hydraulics and Mountain River Engineering, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976","https://openalex.org/I4391767678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073535763","display_name":"Jiancheng Lv","orcid":"https://orcid.org/0000-0001-6551-3884"},"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/I4391767678","display_name":"State Key Laboratory of Hydraulics and Mountain River Engineering","ror":"https://ror.org/02169wb20","country_code":null,"type":"facility","lineage":["https://openalex.org/I24185976","https://openalex.org/I4391767678"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiancheng Lv","raw_affiliation_strings":["College of Computer Science, State Key Laboratory of Hydraulics and Mountain River Engineering, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-6551-3884","affiliations":[{"raw_affiliation_string":"College of Computer Science, State Key Laboratory of Hydraulics and Mountain River Engineering, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976","https://openalex.org/I4391767678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022800038","display_name":"Xi Peng","orcid":"https://orcid.org/0000-0002-5727-2790"},"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/I4391767678","display_name":"State Key Laboratory of Hydraulics and Mountain River Engineering","ror":"https://ror.org/02169wb20","country_code":null,"type":"facility","lineage":["https://openalex.org/I24185976","https://openalex.org/I4391767678"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Peng","raw_affiliation_strings":["College of Computer Science, State Key Laboratory of Hydraulics and Mountain River Engineering, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-5727-2790","affiliations":[{"raw_affiliation_string":"College of Computer Science, State Key Laboratory of Hydraulics and Mountain River Engineering, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976","https://openalex.org/I4391767678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394257","display_name":"Yao Chen","orcid":"https://orcid.org/0000-0002-5869-1612"},"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/I4391767678","display_name":"State Key Laboratory of Hydraulics and Mountain River Engineering","ror":"https://ror.org/02169wb20","country_code":null,"type":"facility","lineage":["https://openalex.org/I24185976","https://openalex.org/I4391767678"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Chen","raw_affiliation_strings":["College of Computer Science, State Key Laboratory of Hydraulics and Mountain River Engineering, Sichuan University, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, State Key Laboratory of Hydraulics and Mountain River Engineering, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976","https://openalex.org/I4391767678"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082641677","display_name":"Shenglan Yang","orcid":"https://orcid.org/0000-0001-8307-3712"},"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/I4391767678","display_name":"State Key Laboratory of Hydraulics and Mountain River Engineering","ror":"https://ror.org/02169wb20","country_code":null,"type":"facility","lineage":["https://openalex.org/I24185976","https://openalex.org/I4391767678"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenglan Yang","raw_affiliation_strings":["College of Computer Science, State Key Laboratory of Hydraulics and Mountain River Engineering, Sichuan University, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, State Key Laboratory of Hydraulics and Mountain River Engineering, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976","https://openalex.org/I4391767678"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4454,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.62459591,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"29","issue":null,"first_page":"1","last_page":"13"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9666000008583069,"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"}},{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9574999809265137,"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/loudness","display_name":"Loudness","score":0.7583432197570801},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7166889905929565},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6687072515487671},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6569329500198364},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.6456291079521179},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5479583144187927},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5428590178489685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45529109239578247},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3637113571166992},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3626102805137634},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1531006097793579}],"concepts":[{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.7583432197570801},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7166889905929565},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6687072515487671},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6569329500198364},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.6456291079521179},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5479583144187927},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5428590178489685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45529109239578247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3637113571166992},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3626102805137634},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1531006097793579},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2020.3030484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3030484","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8299999833106995,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1536680647","https://openalex.org/W1665214252","https://openalex.org/W1836465849","https://openalex.org/W1899309388","https://openalex.org/W2106055371","https://openalex.org/W2124864596","https://openalex.org/W2128838222","https://openalex.org/W2146516687","https://openalex.org/W2166481862","https://openalex.org/W2219249508","https://openalex.org/W2404176928","https://openalex.org/W2407776548","https://openalex.org/W2572771584","https://openalex.org/W2756815061","https://openalex.org/W2771429098","https://openalex.org/W2788283425","https://openalex.org/W2798158991","https://openalex.org/W2798782720","https://openalex.org/W2803270043","https://openalex.org/W2810934215","https://openalex.org/W2890771286","https://openalex.org/W2891901715","https://openalex.org/W2913340405","https://openalex.org/W2921295246","https://openalex.org/W2944850372","https://openalex.org/W2949448715","https://openalex.org/W2952003418","https://openalex.org/W2961433270","https://openalex.org/W2963150697","https://openalex.org/W2963153906","https://openalex.org/W2963391817","https://openalex.org/W2963498646","https://openalex.org/W2963500702","https://openalex.org/W2963558486","https://openalex.org/W2963849887","https://openalex.org/W2963854351","https://openalex.org/W2963877604","https://openalex.org/W2963970896","https://openalex.org/W2964121744","https://openalex.org/W2964199361","https://openalex.org/W2964319599","https://openalex.org/W2968951209","https://openalex.org/W2969574611","https://openalex.org/W2970390610","https://openalex.org/W2983965928","https://openalex.org/W2989608619","https://openalex.org/W2990907756","https://openalex.org/W2990970791","https://openalex.org/W3102612524","https://openalex.org/W3103357565","https://openalex.org/W3123940584","https://openalex.org/W4288350974","https://openalex.org/W4289563769","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6638667902","https://openalex.org/W6684458125","https://openalex.org/W6688816777","https://openalex.org/W6713582272","https://openalex.org/W6744458466","https://openalex.org/W6746430418","https://openalex.org/W6748762347","https://openalex.org/W6752122265","https://openalex.org/W6754881664","https://openalex.org/W6762320557","https://openalex.org/W6770389661","https://openalex.org/W6770963279"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W2030530201","https://openalex.org/W4286629047","https://openalex.org/W4306321456","https://openalex.org/W3046775127","https://openalex.org/W2081647779","https://openalex.org/W4205958290","https://openalex.org/W3096054746"],"abstract_inverted_index":{"One":[0],"practical":[1],"requirement":[2],"of":[3,11,33,69,91,191],"the":[4,9,30,47,62,84,88,92,95,104,109,151,180,188,195],"music":[5,12,21,34,37],"copyright":[6],"management":[7],"is":[8,16,71],"estimation":[10],"relative":[13,38],"loudness,":[14],"which":[15,57,131,140],"mostly":[17],"ignored":[18],"in":[19,94,165,194],"existing":[20],"detection":[22,35,115],"works.":[23],"To":[24,41,119,149],"solve":[25,120],"this":[26,121],"problem,":[27,122],"we":[28,44,107,123],"study":[29],"joint":[31,48,110,152],"task":[32,49,111],"and":[36,55,87,116,138,145,197],"loudness":[39],"estimation.":[40],"be":[42],"specific,":[43],"observe":[45],"that":[46,187],"has":[50],"two":[51,96,133],"characteristics,":[52,154],"i.e.,":[53],"temporality":[54],"hierarchy,":[56],"could":[58],"facilitate":[59],"to":[60,74,83,161,174],"obtain":[61],"solution.":[63],"For":[64],"example,":[65],"a":[66,99],"tiny":[67],"fragment":[68,93],"audio":[70],"temporally":[72],"related":[73],"its":[75],"neighbor":[76],"fragments":[77],"because":[78],"they":[79],"may":[80],"all":[81],"belong":[82],"same":[85],"event,":[86],"event":[89,114],"classes":[90],"tasks":[97],"have":[98],"hierarchical":[100,113,171],"relationship.":[101],"Based":[102],"on":[103,143,179],"above":[105],"observation,":[106],"reformulate":[108],"as":[112,136],"localization":[117],"problem.":[118],"further":[124],"propose":[125],"Hierarchical":[126],"Regulated":[127],"Iterative":[128],"Networks":[129],"(HRIN),":[130],"includes":[132],"variants,":[134],"termed":[135],"HRIN-r":[137],"HRIN-cr,":[139],"are":[141],"based":[142],"recurrent":[144,147],"convolutional":[146],"modules.":[148],"enjoy":[150],"task's":[153],"our":[155,192],"models":[156],"employ":[157],"an":[158],"iterative":[159],"framework":[160],"achieve":[162],"encouraging":[163],"capability":[164],"temporal":[166],"modeling":[167],"while":[168],"designing":[169],"three":[170],"violation":[172],"penalties":[173],"regulate":[175],"hierarchy.":[176],"Extensive":[177],"experiments":[178],"currently":[181],"largest":[182],"dataset":[183],"(i.e.,":[184],"OpenBMAT)":[185],"show":[186],"promising":[189],"performance":[190],"HRIN":[193],"segment-level":[196],"event-level":[198],"evaluations.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}