{"id":"https://openalex.org/W3016005489","doi":"https://doi.org/10.1109/icassp40776.2020.9053065","title":"MT-GCN for Multi-label Audio-tagging with Noisy Labels","display_name":"MT-GCN for Multi-label Audio-tagging with Noisy Labels","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016005489","doi":"https://doi.org/10.1109/icassp40776.2020.9053065","mag":"3016005489"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5037736954","display_name":"Harsh Shrivastava","orcid":"https://orcid.org/0000-0002-8366-6355"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Harsh Shrivastava","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082962427","display_name":"Yifang Yin","orcid":"https://orcid.org/0000-0002-6525-6133"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yfang Yin","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079357056","display_name":"Rajiv Ratn Shah","orcid":"https://orcid.org/0000-0003-1028-9373"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I4210089172","display_name":"Midas Multispeciality Hospital","ror":"https://ror.org/009xczs96","country_code":"IN","type":"healthcare","lineage":["https://openalex.org/I4210089172"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajiv Ratn Shah","raw_affiliation_strings":["MIDAS Lab IIIT-Delhi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIDAS Lab IIIT-Delhi","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I4210089172","https://openalex.org/I68891433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058575315","display_name":"Roger Zimmermann","orcid":"https://orcid.org/0000-0002-7410-2590"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Roger Zimmermann","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9718,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.87939092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"136","last_page":"140"},"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":0.9696999788284302,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9686999917030334,"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/computer-science","display_name":"Computer science","score":0.8614370822906494},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5603705644607544},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5373932123184204},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.5256092548370361},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5078652501106262},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.43288639187812805},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.4193144738674164},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.4113621115684509},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.362345814704895},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.06347426772117615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8614370822906494},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5603705644607544},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5373932123184204},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.5256092548370361},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5078652501106262},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.43288639187812805},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.4193144738674164},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.4113621115684509},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.362345814704895},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.06347426772117615},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1554104313","https://openalex.org/W2107430826","https://openalex.org/W2194775991","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2857761167","https://openalex.org/W2885593519","https://openalex.org/W2896911561","https://openalex.org/W2913159621","https://openalex.org/W2932399282","https://openalex.org/W2963081269","https://openalex.org/W2963735582","https://openalex.org/W2963859210","https://openalex.org/W2982106364","https://openalex.org/W3180479040","https://openalex.org/W6633146083","https://openalex.org/W6687483927","https://openalex.org/W6727253422","https://openalex.org/W6751647823","https://openalex.org/W6753772092","https://openalex.org/W6798291457"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2952760143","https://openalex.org/W2017776670","https://openalex.org/W2347897961","https://openalex.org/W2340870721","https://openalex.org/W2358318464","https://openalex.org/W2979236518","https://openalex.org/W3091955004"],"abstract_inverted_index":{"Multi-label":[0],"audio":[1,15,19,79],"tagging":[2,80],"is":[3],"the":[4,8,40,46,52,66,144,155],"task":[5,35],"of":[6,10,42],"predicting":[7],"types":[9],"sounds":[11],"occurring":[12],"in":[13,45,90,94,123],"an":[14],"clip.":[16],"Recently,":[17],"large-scale":[18],"datasets":[20,49],"such":[21,50],"as":[22,51,62],"Google's":[23],"AudioSet,":[24],"have":[25],"allowed":[26],"researchers":[27],"to":[28,82,98],"use":[29],"deep":[30],"learning":[31],"techniques":[32],"for":[33,78],"this":[34,37,84],"but":[36],"comes":[38],"at":[39],"cost":[41],"label":[43,88,99],"noise":[44],"datasets.":[47],"Audio":[48],"AudioSet":[53],"are":[54,127],"usually":[55],"built":[56],"following":[57],"a":[58,105,130,159],"hierarchical":[59],"structure":[60],"known":[61],"ontology":[63],"which":[64],"captures":[65],"relationships":[67,89,119],"between":[68,120],"different":[69],"sound":[70,121],"events":[71,122],"with":[72],"domain":[73,85,114],"knowledge.":[74],"However,":[75],"existing":[76],"methods":[77,157],"failed":[81],"utilize":[83],"knowledge":[86,115],"about":[87],"their":[91],"models,":[92],"resulting":[93],"models":[95],"being":[96],"sensitive":[97],"noise.":[100],"We":[101,132],"therefore":[102],"present":[103],"MT-GCN,":[104],"Multi-task":[106],"Learning":[107],"based":[108],"Graph":[109],"Convolutional":[110],"Network":[111],"that":[112,151],"learns":[113],"from":[116],"ontology.":[117],"The":[118,147],"our":[124,152],"proposed":[125],"method":[126],"described":[128],"by":[129,158],"graph.":[131],"propose":[133],"two":[134],"ontology-based":[135],"graph":[136],"construction":[137],"methods,":[138],"and":[139],"conduct":[140],"extensive":[141],"experiments":[142],"on":[143],"FSDKaggle2019":[145],"dataset.":[146],"experimental":[148],"results":[149],"show":[150],"approach":[153],"outperforms":[154],"baseline":[156],"significant":[160],"margin.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}