{"id":"https://openalex.org/W4386502669","doi":"https://doi.org/10.18293/dmsviva2023-003","title":"End-to-End Contextual Speech Recognition With Word-Piece-Level Token Selection","display_name":"End-to-End Contextual Speech Recognition With Word-Piece-Level Token Selection","publication_year":2023,"publication_date":"2023-06-29","ids":{"openalex":"https://openalex.org/W4386502669","doi":"https://doi.org/10.18293/dmsviva2023-003"},"language":"en","primary_location":{"id":"doi:10.18293/dmsviva2023-003","is_oa":true,"landing_page_url":"http://doi.org/10.18293/dmsviva2023-003","pdf_url":"http://dx.doi.org/10.18293/dmsviva2023-003","source":{"id":"https://openalex.org/S4386872205","display_name":"Proceedings","issn_l":"2326-3261","issn":["2326-3261"],"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":"International Conferences on Distributed Multimedia Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"http://dx.doi.org/10.18293/dmsviva2023-003","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002005671","display_name":"Zhibin Wu","orcid":"https://orcid.org/0000-0002-9372-0992"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhibin Wu","raw_affiliation_strings":["Institute of Intelligence Science and Technology , School of Computer and Information , Hohai University , Nanjing , China","Institute of Intelligence Science and Technology, School of Computer and Information, Hohai University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Intelligence Science and Technology , School of Computer and Information , Hohai University , Nanjing , China","institution_ids":["https://openalex.org/I163340411"]},{"raw_affiliation_string":"Institute of Intelligence Science and Technology, School of Computer and Information, Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110958246","display_name":"Yang Zou","orcid":"https://orcid.org/0009-0000-5172-0540"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zou","raw_affiliation_strings":["Institute of Intelligence Science and Technology , School of Computer and Information , Hohai University , Nanjing , China","Institute of Intelligence Science and Technology, School of Computer and Information, Hohai University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Intelligence Science and Technology , School of Computer and Information , Hohai University , Nanjing , China","institution_ids":["https://openalex.org/I163340411"]},{"raw_affiliation_string":"Institute of Intelligence Science and Technology, School of Computer and Information, Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101930738","display_name":"Jian Zhou","orcid":"https://orcid.org/0000-0003-3101-6446"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhou","raw_affiliation_strings":["Institute of Intelligence Science and Technology , School of Computer and Information , Hohai University , Nanjing , China","Institute of Intelligence Science and Technology, School of Computer and Information, Hohai University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Intelligence Science and Technology , School of Computer and Information , Hohai University , Nanjing , China","institution_ids":["https://openalex.org/I163340411"]},{"raw_affiliation_string":"Institute of Intelligence Science and Technology, School of Computer and Information, Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101480620","display_name":"Min Wang","orcid":"https://orcid.org/0000-0002-5277-2796"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Wang","raw_affiliation_strings":["Institute of Intelligence Science and Technology , School of Computer and Information , Hohai University , Nanjing , China","Institute of Intelligence Science and Technology, School of Computer and Information, Hohai University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Intelligence Science and Technology , School of Computer and Information , Hohai University , Nanjing , China","institution_ids":["https://openalex.org/I163340411"]},{"raw_affiliation_string":"Institute of Intelligence Science and Technology, School of Computer and Information, Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102017246","display_name":"Xiaoqin Zeng","orcid":"https://orcid.org/0000-0002-4687-901X"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqin Zeng","raw_affiliation_strings":["Institute of Intelligence Science and Technology , School of Computer and Information , Hohai University , Nanjing , China","Institute of Intelligence Science and Technology, School of Computer and Information, Hohai University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Intelligence Science and Technology , School of Computer and Information , Hohai University , Nanjing , China","institution_ids":["https://openalex.org/I163340411"]},{"raw_affiliation_string":"Institute of Intelligence Science and Technology, School of Computer and Information, Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I163340411"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2023","issue":null,"first_page":"81","last_page":"86"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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":0.9976999759674072,"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":0.7996803522109985},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7302079200744629},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6092199683189392},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6002331972122192},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.591681957244873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46602579951286316},{"id":"https://openalex.org/keywords/contextual-design","display_name":"Contextual design","score":0.44740018248558044},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.4464263617992401},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41094905138015747}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7996803522109985},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7302079200744629},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6092199683189392},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6002331972122192},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.591681957244873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46602579951286316},{"id":"https://openalex.org/C71611378","wikidata":"https://www.wikidata.org/wiki/Q5165191","display_name":"Contextual design","level":3,"score":0.44740018248558044},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.4464263617992401},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41094905138015747},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18293/dmsviva2023-003","is_oa":true,"landing_page_url":"http://doi.org/10.18293/dmsviva2023-003","pdf_url":"http://dx.doi.org/10.18293/dmsviva2023-003","source":{"id":"https://openalex.org/S4386872205","display_name":"Proceedings","issn_l":"2326-3261","issn":["2326-3261"],"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":"International Conferences on Distributed Multimedia Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18293/dmsviva2023-003","is_oa":true,"landing_page_url":"http://doi.org/10.18293/dmsviva2023-003","pdf_url":"http://dx.doi.org/10.18293/dmsviva2023-003","source":{"id":"https://openalex.org/S4386872205","display_name":"Proceedings","issn_l":"2326-3261","issn":["2326-3261"],"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":"International Conferences on Distributed Multimedia Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386502669.pdf","grobid_xml":"https://content.openalex.org/works/W4386502669.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1604697534","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W2102113734","https://openalex.org/W2143612262","https://openalex.org/W2293829681","https://openalex.org/W2327501763","https://openalex.org/W2403440562","https://openalex.org/W2586813637","https://openalex.org/W2739427748","https://openalex.org/W2750499125","https://openalex.org/W2775304348","https://openalex.org/W2799800213","https://openalex.org/W2886319145","https://openalex.org/W2889012072","https://openalex.org/W2892009249","https://openalex.org/W2903250132","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2963827914","https://openalex.org/W2972625221","https://openalex.org/W2976324903","https://openalex.org/W3007227084","https://openalex.org/W3022882149","https://openalex.org/W3024172799","https://openalex.org/W3041679645","https://openalex.org/W3097239815","https://openalex.org/W3198007081","https://openalex.org/W4226462878","https://openalex.org/W6623517193","https://openalex.org/W6756319913","https://openalex.org/W6767876487","https://openalex.org/W7027429494"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W2039546652","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W2944691285"],"abstract_inverted_index":{"The":[0],"utilization":[1],"of":[2,37,61,99,164],"dynamic":[3],"contextual":[4,66,75,80,87,100,118,170],"information":[5],"in":[6],"end-to-end":[7],"automatic":[8],"speech":[9],"recognition":[10,38],"has":[11],"been":[12],"an":[13],"active":[14],"research":[15],"topic.Generally,":[16],"the":[17,59,72,79,89,97,112,124,142,152,159],"popular":[18],"Contextual":[19],"LAS":[20],"(CLAS)":[21],"provides":[22],"favorable":[23],"all-neural":[24],"solutions.Nevertheless,":[25],"it":[26,70],"cannot":[27],"be":[28],"extended":[29],"to":[30,77,83,95,110,130],"large":[31],"bias":[32,81,171],"lists":[33],"without":[34],"many":[35],"cases":[36],"errors":[39],"caused":[40],"by":[41,147,154],"similar":[42],"pronunciation":[43],"or":[44],"word":[45,143],"fragment":[46],"repetition.To":[47],"address":[48],"this":[49,51],"limitation,":[50],"paper":[52],"proposes":[53],"a":[54,102,117],"model":[55,136],"called":[56],"Fine-CLAS":[57],"on":[58,85,158],"basis":[60],"CLAS,":[62],"which":[63],"exploits":[64],"wordpiece-level":[65],"knowledge":[67,76],"and":[68,149,151,156,162,169],"fuse":[69],"with":[71,137],"original":[73],"phrase-level":[74],"enable":[78],"module":[82],"focus":[84],"fine-grained":[86],"information.First,":[88],"prefix":[90],"tree":[91],"constraint":[92],"is":[93,108,121],"presented":[94],"reduce":[96,141],"number":[98],"phrases.Then,":[101],"strategy":[103],"for":[104],"word-piece-level":[105,114,125],"token":[106],"selection":[107],"designed":[109],"obtain":[111],"new":[113,132],"embedding":[115,126],"vector.Finally,":[116],"transformation":[119],"chain":[120],"constructed":[122],"between":[123],"vector":[127],"key-value":[128,133],"pairs":[129],"attain":[131],"pairs.The":[134],"proposed":[135],"these":[138],"techniques":[139],"can":[140],"error":[144],"rate":[145],"(WER)":[146],"5.37%":[148],"2.10%,":[150],"F1-score":[153],"1.10%":[155],"2.10%":[157],"datasets":[160],"testclean":[161],"test-other":[163],"LibriSpeech,":[165],"demonstrating":[166],"preferable":[167],"ASR":[168],"performance.":[172]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
