{"id":"https://openalex.org/W7138418878","doi":"https://doi.org/10.1609/aaai.v40i1.36960","title":"Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues","display_name":"Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138418878","doi":"https://doi.org/10.1609/aaai.v40i1.36960"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i1.36960","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i1.36960","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i1.36960","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072485378","display_name":"Zhongjie Ba","orcid":"https://orcid.org/0000-0003-0921-8869"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongjie Ba","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129750066","display_name":"Liang Yi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129669603","display_name":"Peng Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129705520","display_name":"Qingcao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingcao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101888174","display_name":"Qinglong Wang","orcid":"https://orcid.org/0000-0002-7077-5392"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qinglong Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129721317","display_name":"Li Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.5285512,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"1","first_page":"21","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.8551999926567078,"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":0.8551999926567078,"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/T10863","display_name":"Voice and Speech Disorders","score":0.020400000736117363,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.008200000040233135,"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/paralanguage","display_name":"Paralanguage","score":0.9904999732971191},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4799000024795532},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47350001335144043},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.46939998865127563},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42399999499320984},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.41769999265670776},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34860000014305115}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.9904999732971191},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.714900016784668},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5333999991416931},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4799000024795532},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47350001335144043},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45329999923706055},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42399999499320984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41920000314712524},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3467999994754791},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C2778775528","wikidata":"https://www.wikidata.org/wiki/Q5135432","display_name":"Closing (real estate)","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i1.36960","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i1.36960","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/36960","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/36960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i1.36960","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i1.36960","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5639875531196594}],"awards":[{"id":"https://openalex.org/G1803704698","display_name":null,"funder_award_id":"62072395","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2051114290","display_name":null,"funder_award_id":"62172359","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3935748781","display_name":null,"funder_award_id":"U20A20178","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4528407810","display_name":null,"funder_award_id":"62472372","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G659122245","display_name":null,"funder_award_id":"62441238","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Toxic":[0],"speech":[1,19,33,40,45,101,118],"detection":[2,20,184],"has":[3],"become":[4],"a":[5,67,106,111,197,205],"crucial":[6],"challenge":[7],"in":[8,201,209],"maintaining":[9],"safe":[10],"online":[11],"communication":[12],"environments.":[13],"However,":[14],"existing":[15,190],"approaches":[16],"to":[17,38,157],"toxic":[18,44,80,85,100,117,144],"often":[21],"neglect":[22],"the":[23,51,130,138,142,212],"contribution":[24],"of":[25,53,132],"paralinguistic":[26,58,97,180],"cues,":[27],"such":[28],"as":[29],"emotion,":[30],"intonation,":[31],"and":[32,82,96,137,170,204,219],"rate,":[34],"which":[35],"are":[36,47],"key":[37],"detecting":[39],"toxicity.":[41],"Moreover,":[42],"current":[43],"datasets":[46],"predominantly":[48],"text-based,":[49],"limiting":[50],"development":[52],"models":[54],"that":[55,178],"can":[56],"capture":[57],"cues.":[59],"To":[60,161],"address":[61],"these":[62],"challenges,":[63],"we":[64,104,166],"present":[65],"ToxiAlert-Bench,":[66],"large-scale":[68],"audio":[69,74],"dataset":[70,89],"comprising":[71],"over":[72,211],"30,000":[73],"clips":[75],"annotated":[76],"with":[77,110,196],"seven":[78],"major":[79],"categories":[81],"twenty":[83],"fine-grained":[84],"labels.":[86],"Uniquely,":[87],"our":[88],"annotates":[90],"toxicity":[91],"sources\u2014distinguishing":[92],"between":[93],"textual":[94],"content":[95],"origins\u2014for":[98],"comprehensive":[99],"analysis.":[102],"Furthermore,":[103],"propose":[105],"dual-head":[107],"neural":[108],"network":[109],"multi-stage":[112],"training":[113,147,152],"strategy":[114],"tailored":[115],"for":[116,128,140],"detection.":[119],"This":[120],"architecture":[121],"features":[122,181],"two":[123],"task-specific":[124],"classification":[125],"headers:":[126],"one":[127],"identifying":[129],"source":[131],"sensitivity":[133],"(textual":[134],"or":[135],"paralinguistic),":[136],"other":[139],"categorizing":[141],"specific":[143],"type.":[145],"The":[146],"process":[148],"involves":[149],"independent":[150],"head":[151],"followed":[153],"by":[154],"joint":[155],"fine-tuning":[156],"reduce":[158],"task":[159],"interference.":[160],"mitigate":[162],"data":[163],"class":[164],"imbalance,":[165],"incorporate":[167],"class-balanced":[168],"sampling":[169],"weighted":[171],"loss":[172],"functions.":[173],"Our":[174,186],"experimental":[175],"results":[176],"show":[177],"leveraging":[179],"significantly":[182],"improves":[183],"performance.":[185],"method":[187],"consistently":[188],"outperforms":[189],"baselines":[191],"across":[192],"multiple":[193],"evaluation":[194],"metrics,":[195],"21.1%":[198],"relative":[199,207],"improvement":[200],"Macro-F1":[202],"score":[203],"13.0%":[206],"gain":[208],"accuracy":[210],"strongest":[213],"baseline,":[214],"highlighting":[215],"its":[216],"enhanced":[217],"effectiveness":[218],"practical":[220],"applicability.":[221]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2026-03-18T00:00:00"}