{"id":"https://openalex.org/W3093452977","doi":"https://doi.org/10.1145/3490322.3490323","title":"Ensemble Chinese End-to-End Spoken Language Understanding for Abnormal Event Detection from Audio Stream","display_name":"Ensemble Chinese End-to-End Spoken Language Understanding for Abnormal Event Detection from Audio Stream","publication_year":2021,"publication_date":"2021-09-24","ids":{"openalex":"https://openalex.org/W3093452977","doi":"https://doi.org/10.1145/3490322.3490323","mag":"3093452977"},"language":"en","primary_location":{"id":"doi:10.1145/3490322.3490323","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3490322.3490323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 4th International Conference on Big Data Technologies","raw_type":"proceedings-article"},"type":"preprint","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/A5019789898","display_name":"Haoran Wei","orcid":"https://orcid.org/0000-0002-0666-5551"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Haoran Wei","raw_affiliation_strings":["ECE, University of Texas at Dallas, USA and Y-tech, Kuaishou Technology, USA"],"affiliations":[{"raw_affiliation_string":"ECE, University of Texas at Dallas, USA and Y-tech, Kuaishou Technology, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101452102","display_name":"Fei Tao","orcid":"https://orcid.org/0000-0003-4834-8949"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Tao","raw_affiliation_strings":["Y-tech, Kuaishou Technology, USA"],"affiliations":[{"raw_affiliation_string":"Y-tech, Kuaishou Technology, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087054952","display_name":"Ji Liu","orcid":"https://orcid.org/0000-0001-7171-405X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji Liu","raw_affiliation_strings":["Y-tech, Kuaishou Technology, USA"],"affiliations":[{"raw_affiliation_string":"Y-tech, Kuaishou Technology, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002854172","display_name":"Sen Yang","orcid":"https://orcid.org/0000-0003-3222-2268"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sen Yang","raw_affiliation_strings":["Y-tech, Kuaishou Technology, USA"],"affiliations":[{"raw_affiliation_string":"Y-tech, Kuaishou Technology, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078927801","display_name":"Runze Su","orcid":"https://orcid.org/0000-0001-9631-3711"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Runze Su","raw_affiliation_strings":["Y-tech, Kuaishou Technology, USA"],"affiliations":[{"raw_affiliation_string":"Y-tech, Kuaishou Technology, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5019789898"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.14110358,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50206513,"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/T12031","display_name":"Speech and dialogue systems","score":0.9986000061035156,"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":0.8576536178588867},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7765583992004395},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5528256893157959},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5306075215339661},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5304597616195679},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.497908353805542},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49345818161964417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4913569986820221},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4773671329021454},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.41788148880004883},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07628393173217773}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8576536178588867},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7765583992004395},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5528256893157959},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5306075215339661},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5304597616195679},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.497908353805542},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49345818161964417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4913569986820221},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4773671329021454},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.41788148880004883},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07628393173217773},{"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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3490322.3490323","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3490322.3490323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 4th International Conference on Big Data Technologies","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2137871902","https://openalex.org/W2171144711","https://openalex.org/W2766219058","https://openalex.org/W2786839803","https://openalex.org/W2889522887","https://openalex.org/W2891229414","https://openalex.org/W2894164357","https://openalex.org/W2897067191","https://openalex.org/W2898771141","https://openalex.org/W2907228390","https://openalex.org/W2928075308","https://openalex.org/W2951688230","https://openalex.org/W2951882630","https://openalex.org/W2962780374","https://openalex.org/W2963288440","https://openalex.org/W2965002127","https://openalex.org/W2972818416","https://openalex.org/W3004432442","https://openalex.org/W3007328579","https://openalex.org/W3007589762","https://openalex.org/W3015797571","https://openalex.org/W3015885816","https://openalex.org/W3016160783","https://openalex.org/W3016262400","https://openalex.org/W3097306574","https://openalex.org/W3176896803"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W2151749779","https://openalex.org/W3008587939","https://openalex.org/W3196421258","https://openalex.org/W4387301579","https://openalex.org/W2916997151","https://openalex.org/W2944691285","https://openalex.org/W2949174760"],"abstract_inverted_index":{"Conventional":[0],"spoken":[1],"language":[2,31],"understanding":[3,32],"(SLU)":[4],"consist":[5],"of":[6,80,133,162],"two":[7],"stages,":[8],"the":[9,22,78],"first":[10],"stage":[11,24],"maps":[12,25,36],"speech":[13,18,37],"to":[14,27,39,58,72,92,130,147,165],"text":[15,26],"by":[16,29],"automatic":[17],"recognition":[19],"(ASR),":[20],"and":[21,66,136],"second":[23],"intent":[28,40],"natural":[30],"(NLU).":[33],"End-to-end":[34],"SLU":[35,49,62,86,111,119,151,168],"directly":[38],"through":[41],"a":[42,83,108,144,149],"single":[43],"deep":[44],"learning":[45],"model.":[46,169],"Previous":[47],"end-to-end":[48,110,150,167],"models":[50,120],"are":[51],"primarily":[52],"used":[53,113],"for":[54,114],"English":[55],"environment":[56],"due":[57],"lacking":[59],"large":[60,84],"scale":[61,85],"dataset":[63,87],"in":[64,88,96],"Chinese,":[65],"use":[67],"only":[68],"one":[69],"ASR":[70,127],"model":[71,112],"extract":[73],"features":[74,123],"from":[75],"speech.":[76],"With":[77],"help":[79],"Kuaishou":[81],"technology,":[82],"Chinese":[89,115],"is":[90],"collected":[91],"detect":[93],"abnormal":[94],"event":[95],"their":[97],"live":[98],"audio":[99],"stream.":[100],"Based":[101],"on":[102],"this":[103,105],"dataset,":[104],"paper":[106],"proposed":[107,157],"ensemble":[109,118],"environment.":[116],"This":[117,140],"extracted":[121],"hierarchies":[122],"using":[124],"multiple":[125],"pre-trained":[126],"models,":[128],"leading":[129],"better":[131],"representation":[132],"phoneme":[134],"level":[135,138],"word":[137],"information.":[139],"work":[141],"also":[142],"showed":[143],"feasible":[145],"way":[146],"build":[148],"system":[152],"without":[153],"transcribing":[154],"audios.":[155],"The":[156],"approached":[158],"achieve":[159],"9.7\\%":[160],"increase":[161],"accuracy":[163],"compared":[164],"previous":[166]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}