{"id":"https://openalex.org/W4224916736","doi":"https://doi.org/10.1109/icassp43922.2022.9747648","title":"Wikitag: Wikipedia-Based Knowledge Embeddings Towards Improved Acoustic Event Classification","display_name":"Wikitag: Wikipedia-Based Knowledge Embeddings Towards Improved Acoustic Event Classification","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224916736","doi":"https://doi.org/10.1109/icassp43922.2022.9747648"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747648","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/A5100418224","display_name":"Qin Zhang","orcid":"https://orcid.org/0000-0002-6851-3115"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Qin Zhang","raw_affiliation_strings":["Amazon Inc"],"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101986528","display_name":"Qingming Tang","orcid":"https://orcid.org/0000-0002-2670-4917"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingming Tang","raw_affiliation_strings":["Amazon Inc"],"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020775828","display_name":"Chieh-Chi Kao","orcid":"https://orcid.org/0000-0002-1161-3959"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chieh-Chi Kao","raw_affiliation_strings":["Amazon Inc"],"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755311","display_name":"Ming Sun","orcid":"https://orcid.org/0000-0002-5948-2708"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Sun","raw_affiliation_strings":["Amazon Inc"],"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120061442","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0003-4468-3926"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Amazon Inc"],"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100406892","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0001-7578-1970"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["Amazon Inc"],"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100418224"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2458,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.34375987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"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":0.9790999889373779,"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":0.975600004196167,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7927008271217346},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7066575884819031},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6952410340309143},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6346160769462585},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5400103330612183},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46930745244026184},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4518635869026184},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.43452316522598267},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4326164722442627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41583722829818726},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4045085906982422},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07404860854148865}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7927008271217346},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7066575884819031},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6952410340309143},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6346160769462585},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5400103330612183},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46930745244026184},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4518635869026184},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.43452316522598267},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4326164722442627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41583722829818726},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4045085906982422},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07404860854148865},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747648","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":[{"display_name":"Quality Education","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W11298561","https://openalex.org/W1614298861","https://openalex.org/W1622490909","https://openalex.org/W2025341678","https://openalex.org/W2102381086","https://openalex.org/W2103235956","https://openalex.org/W2106241685","https://openalex.org/W2115447976","https://openalex.org/W2524365899","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2767754137","https://openalex.org/W2775747321","https://openalex.org/W2794557536","https://openalex.org/W2930959424","https://openalex.org/W2962910554","https://openalex.org/W2963610932","https://openalex.org/W2964066126","https://openalex.org/W2970912185","https://openalex.org/W3006926732","https://openalex.org/W3015205011","https://openalex.org/W3015295955","https://openalex.org/W3015474227","https://openalex.org/W3102916840","https://openalex.org/W3138521398","https://openalex.org/W3152788712","https://openalex.org/W3161217709","https://openalex.org/W3173233831","https://openalex.org/W3196876847","https://openalex.org/W4245267204","https://openalex.org/W4288348042","https://openalex.org/W6636510571","https://openalex.org/W6747425915","https://openalex.org/W6749879876","https://openalex.org/W6774092362","https://openalex.org/W6840487619"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2988126442","https://openalex.org/W2005801347"],"abstract_inverted_index":{"Acoustic":[0],"event":[1,27],"classification":[2],"(AEC)":[3],"is":[4,135],"the":[5,34,69,105,131,136,140],"task":[6],"of":[7,36],"determining":[8],"whether":[9],"certain":[10],"events":[11],"occur":[12],"in":[13,117,139,152],"an":[14],"audio":[15,43],"clip.":[16],"Inspired":[17],"by":[18,148],"previous":[19],"research":[20],"[1],":[21],"[2],":[22],"[3]":[23],"that":[24,80],"embeddings":[25,49,62,83,94,110],"from":[26,63],"labels":[28],"can":[29],"be":[30],"leveraged":[31],"to":[32,53,59,99],"facilitate":[33],"learning":[35],"new":[37],"detectors":[38],"with":[39,108],"no":[40],"or":[41],"limited":[42],"samples,":[44],"we":[45],"introduce":[46],"Wikipedia-based":[47],"text":[48],"as":[50],"auxiliary":[51],"information":[52,87],"improve":[54],"AEC.":[55],"We":[56,78],"describe":[57],"how":[58],"extract":[60],"label":[61,93,146],"multiple":[64],"Wikipedia":[65,150],"texts,":[66],"and":[67,88,113,124],"formulate":[68],"multi-view":[70,106],"aligned":[71],"AEC":[72,96,141],"problem":[73],"based":[74],"on":[75,103,143],"VGGish":[76],"model.":[77],"show":[79],"our":[81],"\"wikiTAG\"":[82,109],"encode":[84],"rich":[85],"semantic":[86],"are":[89],"more":[90],"informative":[91],"than":[92],"for":[95,127],"tasks.":[97],"Compared":[98],"a":[100,153],"supervised":[101],"baseline":[102],"AudioSet,":[104],"model":[107],"achieves":[111],"7.3%":[112],"1.3%":[114],"relative":[115],"improvement":[116],"mean":[118],"average":[119],"precision":[120],"(mAP)":[121],"using":[122],"10%":[123],"full":[125],"AudioSet":[126],"training,":[128],"respectively.":[129],"To":[130],"author\u2019s":[132],"knowledge,":[133],"this":[134],"first":[137],"work":[138],"domain":[142],"building":[144],"large-scale":[145],"representations":[147],"leveraging":[149],"data":[151],"systematic":[154],"fashion.":[155]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
