{"id":"https://openalex.org/W4372342943","doi":"https://doi.org/10.1109/icassp49357.2023.10094614","title":"Conversation-Oriented ASR with Multi-Look-Ahead CBS Architecture","display_name":"Conversation-Oriented ASR with Multi-Look-Ahead CBS Architecture","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372342943","doi":"https://doi.org/10.1109/icassp49357.2023.10094614"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094614","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5071065862","display_name":"Huaibo Zhao","orcid":"https://orcid.org/0000-0002-3101-4937"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Huaibo Zhao","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007054949","display_name":"Shinya Fujie","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinya Fujie","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087632404","display_name":"Tetsuji Ogawa","orcid":"https://orcid.org/0000-0002-7316-2073"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuji Ogawa","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036873858","display_name":"Jin Sakuma","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jin Sakuma","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109488356","display_name":"Yusuke Kida","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Kida","raw_affiliation_strings":["Line Corporation,Tokyo,Japan","Line Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Line Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"Line Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101188700","display_name":"Tetsunori Kobayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsunori Kobayashi","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5071065862"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04145018,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9959999918937683,"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":0.9943000078201294,"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/conversation","display_name":"Conversation","score":0.8497307300567627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7466433644294739},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6408698558807373},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4556654989719391},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3365126848220825},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3218628764152527},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.11880916357040405},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.0815950334072113},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.06503188610076904},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.05963146686553955}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.8497307300567627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7466433644294739},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6408698558807373},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4556654989719391},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3365126848220825},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3218628764152527},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.11880916357040405},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0815950334072113},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.06503188610076904},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.05963146686553955}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094614","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":36,"referenced_works":["https://openalex.org/W2024490156","https://openalex.org/W2064675550","https://openalex.org/W2144499799","https://openalex.org/W2327501763","https://openalex.org/W2625979394","https://openalex.org/W2766219058","https://openalex.org/W2802023636","https://openalex.org/W2892009249","https://openalex.org/W2935756939","https://openalex.org/W2936774411","https://openalex.org/W2944255943","https://openalex.org/W2946567085","https://openalex.org/W2962780374","https://openalex.org/W2963250244","https://openalex.org/W2972818416","https://openalex.org/W3007328579","https://openalex.org/W3007433671","https://openalex.org/W3015974384","https://openalex.org/W3016010032","https://openalex.org/W3097287883","https://openalex.org/W3097777922","https://openalex.org/W3103005696","https://openalex.org/W3148654612","https://openalex.org/W3161873870","https://openalex.org/W3162899666","https://openalex.org/W3163203022","https://openalex.org/W3198368663","https://openalex.org/W3198442913","https://openalex.org/W4210663600","https://openalex.org/W4297841343","https://openalex.org/W4297841778","https://openalex.org/W4319862469","https://openalex.org/W6623517193","https://openalex.org/W6675365184","https://openalex.org/W6739901393","https://openalex.org/W6802702050"],"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/W2378167147","https://openalex.org/W3210777354","https://openalex.org/W2281307425","https://openalex.org/W2038503502"],"abstract_inverted_index":{"During":[0],"conversations,":[1],"humans":[2],"are":[3,158],"capable":[4],"of":[5,9,15,124],"inferring":[6],"the":[7,10,16,20,28,42,50,117,121,125,152,163,167],"intention":[8],"speaker":[11],"at":[12],"any":[13],"point":[14],"speech":[17,44,51],"to":[18,33,69,74,89,169],"prepare":[19],"following":[21],"action":[22],"promptly.":[23],"Such":[24],"ability":[25],"is":[26,65,133],"also":[27,159],"key":[29],"for":[30,48,151,161],"conversational":[31],"systems":[32],"achieve":[34,55,90],"rhythmic":[35],"and":[36,116,146],"natural":[37],"conversation.":[38],"To":[39,77],"perform":[40,170],"this,":[41],"automatic":[43],"recognition":[45],"(ASR)":[46],"used":[47],"transcribing":[49],"in":[52,104,181],"real-time":[53],"must":[54],"high":[56,63,91,149],"accuracy":[57,64,92],"without":[58,128],"delay.":[59],"In":[60],"streaming":[61,87,139],"ASR,":[62],"assured":[66],"by":[67],"attending":[68],"look-ahead":[70,114,122],"frames,":[71,115],"which":[72,142],"leads":[73],"delay":[75],"increments.":[76],"tackle":[78],"this":[79],"trade-off":[80],"issue,":[81],"we":[82],"propose":[83],"a":[84,107,148],"multiple":[85,153],"latency":[86,154],"ASR":[88],"with":[93],"zero":[94],"look-ahead.":[95,129],"The":[96,130],"proposed":[97,131],"system":[98,132],"contains":[99],"two":[100],"encoders":[101],"that":[102],"operate":[103],"parallel,":[105],"where":[106],"primary":[108,126],"encoder":[109,119,127],"generates":[110],"accurate":[111],"outputs":[112,180],"utilizing":[113],"auxiliary":[118],"recognizes":[120],"portion":[123],"constructed":[134],"based":[135],"on":[136],"contextual":[137],"block":[138,144],"(CBS)":[140],"architecture,":[141],"leverages":[143],"processing":[145],"has":[147],"affinity":[150],"architecture.":[155],"Various":[156],"methods":[157],"studied":[160],"architecting":[162],"system,":[164],"including":[165],"shifting":[166],"network":[168],"as":[171,174,176],"different":[172],"encoders;":[173],"well":[175],"generating":[177],"both":[178],"encoders\u2019":[179],"one":[182],"encoding":[183],"pass.":[184]},"counts_by_year":[],"updated_date":"2026-05-04T08:30:34.212998","created_date":"2025-10-10T00:00:00"}