{"id":"https://openalex.org/W4312534378","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892941","title":"Effective Cross-Utterance Language Modeling for Conversational Speech Recognition","display_name":"Effective Cross-Utterance Language Modeling for Conversational Speech Recognition","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312534378","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892941"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892941","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"2022 International Joint Conference on Neural Networks (IJCNN)","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/A5081032657","display_name":"Bicheng Yan","orcid":"https://orcid.org/0000-0002-3356-7594"},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Bi-Cheng Yan","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan","Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I134161618"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036813887","display_name":"Hsin-Wei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Wei Wang","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan","Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I134161618"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068756690","display_name":"Shih\u2010Hsuan Chiu","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shih-Hsuan Chiu","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan","Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I134161618"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064576196","display_name":"Hsuan-Sheng Chiu","orcid":null},"institutions":[{"id":"https://openalex.org/I92172085","display_name":"Chunghwa Telecom (Taiwan)","ror":"https://ror.org/04f786589","country_code":"TW","type":"company","lineage":["https://openalex.org/I92172085"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsuan-Sheng Chiu","raw_affiliation_strings":["Chunghwa Telecom Laboratories,Taoyuan,Taiwan","Chunghwa Telecom Laboratories, Taoyuan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chunghwa Telecom Laboratories,Taoyuan,Taiwan","institution_ids":["https://openalex.org/I92172085"]},{"raw_affiliation_string":"Chunghwa Telecom Laboratories, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I92172085"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115595070","display_name":"Berlin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Berlin Chen","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan","Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I134161618"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5081032657"],"corresponding_institution_ids":["https://openalex.org/I134161618"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.15659777,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8744412660598755},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7642693519592285},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6165938377380371},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5872999429702759},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5717689394950867},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.55024254322052},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5234212875366211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5134618878364563},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.47436341643333435},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4195253252983093},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12104424834251404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8744412660598755},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7642693519592285},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6165938377380371},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5872999429702759},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5717689394950867},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.55024254322052},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5234212875366211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5134618878364563},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.47436341643333435},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4195253252983093},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12104424834251404},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892941","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W2044818951","https://openalex.org/W2125336414","https://openalex.org/W2402268235","https://openalex.org/W2799473636","https://openalex.org/W2891176389","https://openalex.org/W2892009249","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2936652946","https://openalex.org/W2951672049","https://openalex.org/W2962780374","https://openalex.org/W2963951265","https://openalex.org/W2964110616","https://openalex.org/W2979826702","https://openalex.org/W2990391581","https://openalex.org/W3024308166","https://openalex.org/W3034775979","https://openalex.org/W3094852745","https://openalex.org/W3096099419","https://openalex.org/W3101648800","https://openalex.org/W3141961557","https://openalex.org/W3161365423","https://openalex.org/W3167533889","https://openalex.org/W3189689281","https://openalex.org/W3196473441","https://openalex.org/W3196495667","https://openalex.org/W3198700088","https://openalex.org/W3200601846","https://openalex.org/W3200895333","https://openalex.org/W3212613829","https://openalex.org/W3214532454","https://openalex.org/W4249803144","https://openalex.org/W6623517193","https://openalex.org/W6678809451","https://openalex.org/W6731780175","https://openalex.org/W6750226204","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6761380950","https://openalex.org/W6770528390","https://openalex.org/W6799082546"],"related_works":["https://openalex.org/W1968552888","https://openalex.org/W2374116601","https://openalex.org/W3093134843","https://openalex.org/W2772323916","https://openalex.org/W1511346092","https://openalex.org/W1527532029","https://openalex.org/W2529301793","https://openalex.org/W2378167147","https://openalex.org/W3210777354","https://openalex.org/W3133700904"],"abstract_inverted_index":{"Conversational":[0],"speech":[1,80],"normally":[2],"is":[3,91],"embodied":[4],"with":[5,31],"loose":[6],"syntactic":[7],"structures":[8],"at":[9],"the":[10,46,51,58,99,107,126,143,150,163,170,197],"utterance":[11,105],"level":[12],"but":[13,194],"simultaneously":[14],"exhibits":[15],"topical":[16],"coherence":[17],"relations":[18],"across":[19,65],"consecutive":[20],"utterances.":[21],"Prior":[22],"work":[23],"has":[24],"shown":[25],"that":[26],"capturing":[27],"longer":[28],"context":[29],"information":[30],"a":[32,87,103,116,133,154],"recurrent":[33],"neural":[34],"network":[35],"or":[36],"long":[37],"short-term":[38],"memory":[39],"language":[40,76],"model":[41],"(LM)":[42],"may":[43],"suffer":[44],"from":[45,153],"recent":[47],"bias":[48],"while":[49],"excluding":[50],"long-range":[52],"context.":[53],"In":[54],"order":[55],"to":[56,95,146,168,179],"capture":[57],"long-term":[59],"semantic":[60,108],"interactions":[61],"among":[62],"words":[63],"and":[64,97,106,172],"utterances,":[66],"we":[67,124],"put":[68],"forward":[69],"disparate":[70],"conversation":[71,113],"history":[72,114],"fusion":[73],"methods":[74,176,186],"for":[75,200],"modeling":[77],"in":[78,115,177],"automatic":[79],"recognition":[81],"(ASR)":[82],"of":[83,102,110,149,174],"conversational":[84,201],"speech.":[85,202],"Furthermore,":[86],"novel":[88],"audio-fusion":[89],"mechanism":[90],"introduced,":[92],"which":[93],"manages":[94],"fuse":[96],"utilize":[98],"acoustic":[100],"embeddings":[101],"current":[104,181],"content":[109],"its":[111],"corresponding":[112],"cooperative":[117],"way.":[118],"To":[119],"flesh":[120],"out":[121],"our":[122,175],"ideas,":[123],"frame":[125],"ASR":[127,198],"N-best":[128,156],"hypothesis":[129,152,157],"rescoring":[130],"task":[131],"as":[132,142],"prediction":[134],"problem,":[135],"leveraging":[136],"BERT,":[137],"an":[138],"iconic":[139],"pre-trained":[140],"LM,":[141],"ingredient":[144],"vehicle":[145],"facilitate":[147],"selection":[148],"oracle":[151],"given":[155],"list.":[158],"Empirical":[159],"experiments":[160],"conducted":[161],"on":[162],"AMI":[164],"benchmark":[165],"dataset":[166],"seem":[167],"demonstrate":[169],"feasibility":[171],"efficacy":[173],"relation":[178],"some":[180],"top-of-line":[182],"methods.":[183],"The":[184],"proposed":[185],"not":[187],"only":[188],"achieve":[189],"significant":[190],"inference":[191],"time":[192],"reduction":[193],"also":[195],"improve":[196],"performance":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}