{"id":"https://openalex.org/W4392904101","doi":"https://doi.org/10.1109/icassp48485.2024.10448289","title":"Voice Toxicity Detection Using Multi-Task Learning","display_name":"Voice Toxicity Detection Using Multi-Task Learning","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904101","doi":"https://doi.org/10.1109/icassp48485.2024.10448289"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5081255157","display_name":"Mahesh Kumar Nandwana","orcid":null},"institutions":[{"id":"https://openalex.org/I142600864","display_name":"College of San Mateo","ror":"https://ror.org/01gwn6z70","country_code":"US","type":"education","lineage":["https://openalex.org/I142600864"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mahesh Kumar Nandwana","raw_affiliation_strings":["Roblox,San Mateo,CA","Roblox, San Mateo, CA"],"affiliations":[{"raw_affiliation_string":"Roblox,San Mateo,CA","institution_ids":["https://openalex.org/I142600864"]},{"raw_affiliation_string":"Roblox, San Mateo, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101585745","display_name":"Yifan He","orcid":"https://orcid.org/0000-0002-9171-3502"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]},{"id":"https://openalex.org/I142600864","display_name":"College of San Mateo","ror":"https://ror.org/01gwn6z70","country_code":"US","type":"education","lineage":["https://openalex.org/I142600864"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan He","raw_affiliation_strings":["Roblox,San Mateo,CA","Carnegie Mellon University, Pittsburgh, PA","Roblox, San Mateo, CA"],"affiliations":[{"raw_affiliation_string":"Roblox,San Mateo,CA","institution_ids":["https://openalex.org/I142600864"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Roblox, San Mateo, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101559537","display_name":"Joseph Liu","orcid":"https://orcid.org/0009-0006-7994-7716"},"institutions":[{"id":"https://openalex.org/I142600864","display_name":"College of San Mateo","ror":"https://ror.org/01gwn6z70","country_code":"US","type":"education","lineage":["https://openalex.org/I142600864"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph Liu","raw_affiliation_strings":["Roblox,San Mateo,CA","Roblox, San Mateo, CA"],"affiliations":[{"raw_affiliation_string":"Roblox,San Mateo,CA","institution_ids":["https://openalex.org/I142600864"]},{"raw_affiliation_string":"Roblox, San Mateo, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100321671","display_name":"Xiao Yu","orcid":"https://orcid.org/0000-0002-0314-9295"},"institutions":[{"id":"https://openalex.org/I142600864","display_name":"College of San Mateo","ror":"https://ror.org/01gwn6z70","country_code":"US","type":"education","lineage":["https://openalex.org/I142600864"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Yu","raw_affiliation_strings":["Roblox,San Mateo,CA","Roblox, San Mateo, CA"],"affiliations":[{"raw_affiliation_string":"Roblox,San Mateo,CA","institution_ids":["https://openalex.org/I142600864"]},{"raw_affiliation_string":"Roblox, San Mateo, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101835397","display_name":"Charles Shang","orcid":null},"institutions":[{"id":"https://openalex.org/I142600864","display_name":"College of San Mateo","ror":"https://ror.org/01gwn6z70","country_code":"US","type":"education","lineage":["https://openalex.org/I142600864"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Shang","raw_affiliation_strings":["Roblox,San Mateo,CA","Roblox, San Mateo, CA"],"affiliations":[{"raw_affiliation_string":"Roblox,San Mateo,CA","institution_ids":["https://openalex.org/I142600864"]},{"raw_affiliation_string":"Roblox, San Mateo, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079322923","display_name":"Eloi Du Bois","orcid":"https://orcid.org/0009-0009-7169-3370"},"institutions":[{"id":"https://openalex.org/I142600864","display_name":"College of San Mateo","ror":"https://ror.org/01gwn6z70","country_code":"US","type":"education","lineage":["https://openalex.org/I142600864"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eloi Du Bois","raw_affiliation_strings":["Roblox,San Mateo,CA","Roblox, San Mateo, CA"],"affiliations":[{"raw_affiliation_string":"Roblox,San Mateo,CA","institution_ids":["https://openalex.org/I142600864"]},{"raw_affiliation_string":"Roblox, San Mateo, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101915674","display_name":"Morgan McGuire","orcid":"https://orcid.org/0000-0003-1074-0953"},"institutions":[{"id":"https://openalex.org/I142600864","display_name":"College of San Mateo","ror":"https://ror.org/01gwn6z70","country_code":"US","type":"education","lineage":["https://openalex.org/I142600864"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Morgan McGuire","raw_affiliation_strings":["Roblox,San Mateo,CA","Roblox, San Mateo, CA"],"affiliations":[{"raw_affiliation_string":"Roblox,San Mateo,CA","institution_ids":["https://openalex.org/I142600864"]},{"raw_affiliation_string":"Roblox, San Mateo, CA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052113444","display_name":"K. Sham Bhat","orcid":"https://orcid.org/0009-0000-1221-7256"},"institutions":[{"id":"https://openalex.org/I142600864","display_name":"College of San Mateo","ror":"https://ror.org/01gwn6z70","country_code":"US","type":"education","lineage":["https://openalex.org/I142600864"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kiran Bhat","raw_affiliation_strings":["Roblox,San Mateo,CA","Roblox, San Mateo, CA"],"affiliations":[{"raw_affiliation_string":"Roblox,San Mateo,CA","institution_ids":["https://openalex.org/I142600864"]},{"raw_affiliation_string":"Roblox, San Mateo, CA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5081255157"],"corresponding_institution_ids":["https://openalex.org/I142600864"],"apc_list":null,"apc_paid":null,"fwci":1.0911,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79353734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"331","last_page":"335"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9970999956130981,"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"}},"topics":[{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9970999956130981,"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/T11309","display_name":"Music and Audio Processing","score":0.9927999973297119,"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":0.9889000058174133,"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":0.8093788623809814},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6624146103858948},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5858996510505676},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5841550827026367},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.527900755405426},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48346051573753357},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.44941645860671997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4254250228404999},{"id":"https://openalex.org/keywords/multiclass-classification","display_name":"Multiclass classification","score":0.419017493724823},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3760962188243866},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3717988431453705},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.24615108966827393},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.204697847366333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8093788623809814},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6624146103858948},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5858996510505676},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5841550827026367},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.527900755405426},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48346051573753357},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.44941645860671997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4254250228404999},{"id":"https://openalex.org/C123860398","wikidata":"https://www.wikidata.org/wiki/Q6934605","display_name":"Multiclass classification","level":3,"score":0.419017493724823},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3760962188243866},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3717988431453705},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.24615108966827393},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.204697847366333},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2034940213","https://openalex.org/W2146334809","https://openalex.org/W2407023693","https://openalex.org/W2888781539","https://openalex.org/W2904937466","https://openalex.org/W2963677766","https://openalex.org/W2972625221","https://openalex.org/W2978017171","https://openalex.org/W3001639638","https://openalex.org/W3036601975","https://openalex.org/W3087148478","https://openalex.org/W3161587393","https://openalex.org/W3177971705","https://openalex.org/W3197580070","https://openalex.org/W3209984917","https://openalex.org/W4234433632","https://openalex.org/W4297805866","https://openalex.org/W4297841625","https://openalex.org/W4312836360","https://openalex.org/W4366999503","https://openalex.org/W6745995898","https://openalex.org/W6759579507","https://openalex.org/W6768851824","https://openalex.org/W6776302503","https://openalex.org/W6780218876","https://openalex.org/W6782990278","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2131711534","https://openalex.org/W2559837139","https://openalex.org/W1151175420","https://openalex.org/W2407342067"],"abstract_inverted_index":{"Social":[0],"communication":[1],"systems":[2],"must":[3],"identify":[4],"toxic":[5,99,114],"voice":[6,23],"audio":[7,27],"to":[8,105],"support":[9],"moderation":[10],"that":[11,94,109,126],"protects":[12],"the":[13,38,41,61,127,131],"safety":[14],"and":[15,32,34,44,70,79,101,120],"civility":[16],"of":[17,98,133,146],"their":[18],"communities.":[19],"Toxicity":[20],"classification":[21,92,122],"for":[22,56,142],"depends":[24],"on":[25,111],"both":[26],"style,":[28],"such":[29,36],"as":[30,37],"volume":[31],"tone,":[33],"content,":[35],"words":[39],"in":[40,45],"speech":[42,67],"individually":[43],"context.":[46],"We":[47,124,136],"introduce":[48],"a":[49,75,89,139],"novel":[50],"end-to-end":[51],"multi-task":[52],"learning":[53],"(MTL)":[54],"paradigm":[55],"audio-based":[57],"toxicity":[58,91],"detection,":[59],"addressing":[60],"challenges":[62],"associated":[63],"with":[64],"existing":[65],"automatic":[66],"recognition":[68],"(ASR)":[69],"text-based":[71],"systems.":[72],"By":[73],"employing":[74],"hard":[76],"parameter-sharing":[77],"backbone":[78],"flexible":[80],"soft-attention":[81],"task":[82,93,108],"adapters,":[83],"our":[84],"model":[85],"performs":[86],"two":[87],"tasks:":[88],"multi-label":[90],"targets":[95],"specific":[96],"categories":[97],"behavior,":[100],"an":[102],"auxiliary":[103],"Audio":[104],"Keyword":[106],"detection":[107],"focuses":[110],"transcribing":[112],"only":[113],"keywords,":[115],"thereby":[116],"enhancing":[117],"computational":[118],"efficiency":[119],"complementing":[121],"output.":[123],"observe":[125],"classifier":[128],"significantly":[129],"improves":[130],"quality":[132],"keyword":[134],"detection.":[135],"also":[137],"contribute":[138],"data":[140],"pipeline":[141],"automated":[143],"offline":[144],"labeling":[145],"training":[147],"sets.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}