{"id":"https://openalex.org/W4224917059","doi":"https://doi.org/10.1109/icassp43922.2022.9746431","title":"Pseudo Strong Labels for Large Scale Weakly Supervised Audio Tagging","display_name":"Pseudo Strong Labels for Large Scale Weakly Supervised Audio Tagging","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224917059","doi":"https://doi.org/10.1109/icassp43922.2022.9746431"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746431","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5080154283","display_name":"Heinrich Dinkel","orcid":"https://orcid.org/0000-0003-4330-8980"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Heinrich Dinkel","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China","Xiaomi Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113948981","display_name":"Zhiyong Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Yan","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China","Xiaomi Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100673739","display_name":"Yongqing Wang","orcid":"https://orcid.org/0000-0003-1164-0137"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqing Wang","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China","Xiaomi Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778479","display_name":"Junbo Zhang","orcid":"https://orcid.org/0000-0001-5947-1374"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junbo Zhang","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China","Xiaomi Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362608","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0003-2335-0946"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China","Xiaomi Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5080154283"],"corresponding_institution_ids":["https://openalex.org/I862669128"],"apc_list":null,"apc_paid":null,"fwci":0.6137,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.63538705,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"336","last_page":"340"},"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":0.9995999932289124,"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":0.9955999851226807,"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":0.7788807153701782},{"id":"https://openalex.org/keywords/psl","display_name":"PSL","score":0.705085277557373},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6366809606552124},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.5377402901649475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5064512491226196},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.43852126598358154},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4205496311187744},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.417496919631958},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.41628652811050415},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3756210505962372},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11157187819480896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7788807153701782},{"id":"https://openalex.org/C10464949","wikidata":"https://www.wikidata.org/wiki/Q1914781","display_name":"PSL","level":2,"score":0.705085277557373},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6366809606552124},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.5377402901649475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5064512491226196},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.43852126598358154},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4205496311187744},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.417496919631958},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.41628652811050415},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3756210505962372},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11157187819480896},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746431","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":30,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1821462560","https://openalex.org/W2593116425","https://openalex.org/W2765407302","https://openalex.org/W2770119437","https://openalex.org/W2936774411","https://openalex.org/W2963163009","https://openalex.org/W2973109987","https://openalex.org/W2982343573","https://openalex.org/W3040498734","https://openalex.org/W3094550259","https://openalex.org/W3097495228","https://openalex.org/W3126565544","https://openalex.org/W3154596443","https://openalex.org/W3162999565","https://openalex.org/W3168547821","https://openalex.org/W3169064633","https://openalex.org/W3196974791","https://openalex.org/W4205689591","https://openalex.org/W4295312788","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6745136726","https://openalex.org/W6746278845","https://openalex.org/W6766978945","https://openalex.org/W6779503413","https://openalex.org/W6783462664","https://openalex.org/W6790117948","https://openalex.org/W6790830454","https://openalex.org/W6793736971"],"related_works":["https://openalex.org/W3004330880","https://openalex.org/W2906414647","https://openalex.org/W2996101188","https://openalex.org/W2312247860","https://openalex.org/W4312840159","https://openalex.org/W3093874938","https://openalex.org/W2517964802","https://openalex.org/W2324290803","https://openalex.org/W2320630492","https://openalex.org/W1970248180"],"abstract_inverted_index":{"Large-scale":[0],"audio":[1,49],"tagging":[2],"datasets":[3,121],"inevitably":[4],"contain":[5],"imperfect":[6],"labels,":[7],"such":[8],"as":[9],"clip-wise":[10],"annotated":[11],"(temporally":[12],"weak)":[13],"tags":[14],"with":[15,111],"no":[16],"exact":[17],"on-":[18],"and":[19],"offsets,":[20],"due":[21],"to":[22,118],"a":[23,35,58,69,86],"high":[24],"manual":[25],"labeling":[26],"cost.":[27],"This":[28],"work":[29],"proposes":[30],"pseudo":[31],"strong":[32],"labels":[33],"(PSL),":[34],"simple":[36],"label":[37],"augmentation":[38],"framework":[39],"that":[40,100,108],"enhances":[41],"the":[42,119],"supervision":[43,67],"quality":[44],"for":[45,68],"large-scale":[46],"weakly":[47,60,125],"supervised":[48,61],"tagging.":[50],"A":[51],"machine":[52],"annotator":[53],"is":[54,96],"first":[55],"trained":[56,110,126],"on":[57],"large":[59],"dataset,":[62],"which":[63,98],"then":[64],"provides":[65],"finer":[66],"student":[70],"model.":[71],"Using":[72],"PSL":[73,101,112],"we":[74,106],"achieve":[75],"an":[76],"mAP":[77],"of":[78,83],"35.95":[79],"balanced":[80],"train":[81],"subsets":[82],"Audioset":[84],"using":[85],"MobileNetV2":[87],"backend,":[88],"significantly":[89],"outperforming":[90],"approaches":[91],"without":[92],"PSL.":[93],"An":[94],"analysis":[95],"provided":[97],"reveals":[99],"mitigates":[102],"missing":[103],"labels.":[104],"Lastly,":[105],"show":[107],"models":[109],"are":[113],"also":[114],"superior":[115],"at":[116],"generalizing":[117],"Freesound":[120],"(FSD)":[122],"than":[123],"their":[124],"counterparts.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}