{"id":"https://openalex.org/W4414009019","doi":"https://doi.org/10.1109/icetis66286.2025.11144029","title":"Efficient Recognition of Vulgar Words in End-to-End ASR","display_name":"Efficient Recognition of Vulgar Words in End-to-End ASR","publication_year":2025,"publication_date":"2025-06-27","ids":{"openalex":"https://openalex.org/W4414009019","doi":"https://doi.org/10.1109/icetis66286.2025.11144029"},"language":"en","primary_location":{"id":"doi:10.1109/icetis66286.2025.11144029","doi":"https://doi.org/10.1109/icetis66286.2025.11144029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icetis66286.2025.11144029","pdf_url":null,"source":{"id":"https://openalex.org/S7407088874","display_name":"International Conference on Electronic Technology and Information Science (ICETIS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2025 10th International Conference on Electronic Technology and Information Science (ICETIS)","raw_type":"proceedings-article"},"volume":null,"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/A5100333729","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0002-5214-2268","observed_orcids":["https://orcid.org/0000-0002-5214-2268"]},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":"CN","type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Zhang","raw_affiliation_strings":["China Telecom Co.,Ltd. Xinjiang Branch Network Monitoring and Maintenance Center (Network Security Operations Center)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Co.,Ltd. Xinjiang Branch Network Monitoring and Maintenance Center (Network Security Operations Center)","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407453","display_name":"Dong Li","orcid":"https://orcid.org/0000-0002-5084-3781","observed_orcids":["https://orcid.org/0000-0002-5084-3781"]},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":"CN","type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Li","raw_affiliation_strings":["China Telecom Co.,Ltd. Xinjiang Branch Network Monitoring and Maintenance Center (Network Security Operations Center)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Co.,Ltd. Xinjiang Branch Network Monitoring and Maintenance Center (Network Security Operations Center)","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xin An","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":"CN","type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin An","raw_affiliation_strings":["China Telecom Co.,Ltd. Xinjiang Branch Network Monitoring and Maintenance Center (Network Security Operations Center)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Co.,Ltd. Xinjiang Branch Network Monitoring and Maintenance Center (Network Security Operations Center)","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033446651","display_name":"Zhou Tao","orcid":"https://orcid.org/0000-0001-9232-0068","observed_orcids":["https://orcid.org/0000-0001-9232-0068"]},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":"CN","type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhou","raw_affiliation_strings":["China Telecom Co.,Ltd. Xinjiang Branch Network Monitoring and Maintenance Center (Network Security Operations Center)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Co.,Ltd. Xinjiang Branch Network Monitoring and Maintenance Center (Network Security Operations Center)","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044077757","display_name":"Jin Xiao","orcid":"https://orcid.org/0000-0003-3535-6552","observed_orcids":["https://orcid.org/0000-0003-3535-6552"]},"institutions":[{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":"CN","type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Jin","raw_affiliation_strings":["China Telecom Co., Ltd. Cloud and Network Communication Center,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Co., Ltd. Cloud and Network Communication Center,Beijing,China","institution_ids":["https://openalex.org/I4387153335"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yachao Guo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yachao Guo","raw_affiliation_strings":["China Energy Investment Corp. Xinjiang Ganquanbao Integrated Energy,Ürümqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Energy Investment Corp. Xinjiang Ganquanbao Integrated Energy,Ürümqi,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20749548,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"346","last_page":"349"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0,"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/profanity-detection","display_name":"profanity detection","score":0.7820000052452087},{"id":"https://openalex.org/keywords/end-to-end-speech-recognition","display_name":"end-to-end speech recognition","score":0.8519999980926514},{"id":"https://openalex.org/keywords/aho-corasick-algorithm","display_name":"Aho-Corasick algorithm","score":0.9760000109672546},{"id":"https://openalex.org/keywords/cross-domain-recognition","display_name":"cross-domain recognition","score":0.5410000085830688},{"id":"https://openalex.org/keywords/decoding-errors","display_name":"decoding errors","score":0.33899998664855957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6562485098838806},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.629025399684906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6021728515625},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3874117136001587},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.33362194895744324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30012986063957214},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06070345640182495}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icetis66286.2025.11144029","doi":"https://doi.org/10.1109/icetis66286.2025.11144029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icetis66286.2025.11144029","pdf_url":null,"source":{"id":"https://openalex.org/S7407088874","display_name":"International Conference on Electronic Technology and Information Science (ICETIS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2025 10th International Conference on Electronic Technology and Information Science (ICETIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2024490156","https://openalex.org/W2526425061","https://openalex.org/W2766219058","https://openalex.org/W2903250132","https://openalex.org/W2962760690","https://openalex.org/W2962780374","https://openalex.org/W2973072704","https://openalex.org/W3014344307","https://openalex.org/W3142545740","https://openalex.org/W3156731511","https://openalex.org/W4221167707","https://openalex.org/W4385488828"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W3196421258","https://openalex.org/W4387301579","https://openalex.org/W2763956190","https://openalex.org/W3008587939","https://openalex.org/W3204019825","https://openalex.org/W4404782863"],"abstract_inverted_index":{"The":[0],"accurate":[1],"identification":[2],"of":[3,116,138],"infrequent":[4,35,94],"profane":[5,95,149],"expressions":[6,119],"presents":[7],"a":[8],"persistent":[9],"challenge":[10],"for":[11,21,34,147],"end-to-end":[12],"automatic":[13],"speech":[14,131],"recognition":[15,127,145],"(ASR)":[16],"systems.":[17,155],"While":[18],"existing":[19],"techniques":[20],"rare":[22,117,148],"term":[23],"processing":[24],"have":[25],"enhanced":[26],"general":[27],"rareword":[28],"detection,":[29],"their":[30,126],"efficacy":[31],"diminishes":[32],"significantly":[33],"vulgar":[36,82,118],"terms,":[37],"particularly":[38],"those":[39],"that":[40],"are":[41],"lengthy":[42],"and":[43,78,88],"exhibit":[44],"low":[45],"occurrence":[46],"rates.":[47],"Furthermore,":[48],"research":[49],"frequently":[50],"neglects":[51],"the":[52,70,113,136,139,144],"mismatch":[53],"rate":[54,115],"associated":[55],"with":[56,104],"these":[57],"terms":[58],"during":[59],"search":[60],"algorithm":[61],"execution.":[62],"This":[63],"work":[64],"introduces":[65],"an":[66],"efficient":[67],"methodology":[68],"leveraging":[69],"Aho-Corasick":[71],"algorithm.":[72],"Our":[73],"approach":[74,103],"elevates":[75],"ASR":[76,154],"efficiency":[77],"decoding":[79],"precision":[80],"concerning":[81],"vocabulary":[83],"by":[84],"minimizing":[85],"matching":[86],"failures":[87],"applying":[89],"length-dependent":[90],"weighting":[91],"coefficients":[92],"to":[93],"words,":[96],"thereby":[97],"mitigating":[98],"erroneous":[99],"insertions.":[100],"Integrating":[101],"this":[102],"internal":[105],"language":[106],"model":[107],"estimation":[108],"yields":[109],"substantial":[110],"gains":[111],"in":[112,129,142],"detection":[114],"within":[120,151],"specialized":[121],"domains,":[122],"as":[123,125],"well":[124],"accuracy":[128],"cross-domain":[130],"utterances.":[132],"Empirical":[133],"evaluations":[134],"validate":[135],"effectiveness":[137],"proposed":[140],"technique":[141],"augmenting":[143],"capabilities":[146],"words":[150],"fully":[152],"neural":[153]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}