{"id":"https://openalex.org/W4226462878","doi":"https://doi.org/10.1109/asru51503.2021.9687915","title":"Tree-Constrained Pointer Generator for End-to-End Contextual Speech Recognition","display_name":"Tree-Constrained Pointer Generator for End-to-End Contextual Speech Recognition","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4226462878","doi":"https://doi.org/10.1109/asru51503.2021.9687915"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9687915","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687915","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5077772423","display_name":"Guangzhi Sun","orcid":"https://orcid.org/0000-0002-5886-056X"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guangzhi Sun","raw_affiliation_strings":["Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460206","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-7730-5131"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip C. Woodland","raw_affiliation_strings":["Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":2.4097,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.91515712,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"780","last_page":"787"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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":0.9984999895095825,"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":0.7721107006072998},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.6292505264282227},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6120445132255554},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5368865728378296},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4869862496852875},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.47321146726608276},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4704799950122833},{"id":"https://openalex.org/keywords/biasing","display_name":"Biasing","score":0.46894311904907227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3585609793663025},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24747788906097412},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.13961592316627502},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08455270528793335},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07577770948410034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7721107006072998},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.6292505264282227},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6120445132255554},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5368865728378296},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4869862496852875},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47321146726608276},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4704799950122833},{"id":"https://openalex.org/C20254490","wikidata":"https://www.wikidata.org/wiki/Q719550","display_name":"Biasing","level":3,"score":0.46894311904907227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3585609793663025},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24747788906097412},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.13961592316627502},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08455270528793335},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07577770948410034},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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:10.1109/asru51503.2021.9687915","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687915","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":61,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1686810756","https://openalex.org/W1942035323","https://openalex.org/W2143612262","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2577366047","https://openalex.org/W2606974598","https://openalex.org/W2748816379","https://openalex.org/W2750499125","https://openalex.org/W2799800213","https://openalex.org/W2801746067","https://openalex.org/W2810084418","https://openalex.org/W2883586237","https://openalex.org/W2886180730","https://openalex.org/W2886319145","https://openalex.org/W2889012072","https://openalex.org/W2889282842","https://openalex.org/W2903250132","https://openalex.org/W2936774411","https://openalex.org/W2962760690","https://openalex.org/W2962780374","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963240019","https://openalex.org/W2963403664","https://openalex.org/W2963827914","https://openalex.org/W2972625221","https://openalex.org/W2972730581","https://openalex.org/W2973172693","https://openalex.org/W2992739892","https://openalex.org/W3007227084","https://openalex.org/W3007905516","https://openalex.org/W3008323921","https://openalex.org/W3015686596","https://openalex.org/W3015747801","https://openalex.org/W3016234571","https://openalex.org/W3022882149","https://openalex.org/W3042416212","https://openalex.org/W3095962459","https://openalex.org/W3096758108","https://openalex.org/W3097239815","https://openalex.org/W3097794466","https://openalex.org/W3140235797","https://openalex.org/W3152221657","https://openalex.org/W3162639446","https://openalex.org/W3163560333","https://openalex.org/W3198004110","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6629717138","https://openalex.org/W6637373629","https://openalex.org/W6676562027","https://openalex.org/W6728030952","https://openalex.org/W6737294268","https://openalex.org/W6739901393","https://openalex.org/W6777472801","https://openalex.org/W6777568614","https://openalex.org/W6784885159","https://openalex.org/W7027429494"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W2142481367","https://openalex.org/W3196321793","https://openalex.org/W3080705045","https://openalex.org/W2385527937","https://openalex.org/W2005880840","https://openalex.org/W3177678247","https://openalex.org/W2507465767"],"abstract_inverted_index":{"Contextual":[0],"knowledge":[1,26],"is":[2,21,140],"important":[3],"for":[4],"real-world":[5],"automatic":[6],"speech":[7],"recognition":[8],"(ASR)":[9],"applications.":[10],"In":[11],"this":[12],"paper,":[13],"a":[14,28,43,64,103,106,154],"novel":[15],"tree-constrained":[16],"pointer":[17],"generator":[18],"(TCPGen)":[19],"component":[20],"proposed":[22],"that":[23,116],"incorpo-rates":[24],"such":[25],"as":[27,58],"list":[29],"of":[30,100],"biasing":[31,49,79,93,137,147],"words":[32,50,80,94,148],"into":[33,51],"both":[34],"attention-based":[35],"encoder-decoder":[36],"and":[37,62,70,86,128,149,151,160],"transducer":[38],"end-to-end":[39],"ASR":[40,73],"models":[41],"in":[42,129],"neural-symbolic":[44],"way.":[45],"TCPGen":[46,117,139],"structures":[47],"the":[48,68,71,89,98,126,136],"an":[52,101],"efficient":[53],"prefix":[54],"tree":[55,69],"to":[56,76,108,125,157],"serve":[57],"its":[59],"symbolic":[60],"input":[61],"creates":[63],"neu-ral":[65],"shortcut":[66],"between":[67],"final":[72],"output":[74],"distribution":[75],"facilitate":[77],"recognising":[78],"during":[81],"decoding.":[82],"Systems":[83],"were":[84,95],"trained":[85],"evaluated":[87],"on":[88,135],"Librispeech":[90],"corpus":[91],"where":[92],"extracted":[96],"at":[97],"scales":[99],"utterance,":[102],"chapter,":[104],"or":[105],"book":[107],"simulate":[109],"different":[110],"application":[111],"scenarios.":[112],"Experimental":[113],"results":[114],"showed":[115],"consistently":[118],"improved":[119],"word":[120],"error":[121],"rates":[122],"(WERs)":[123],"compared":[124],"baselines,":[127],"particular,":[130],"achieved":[131],"sig-nificant":[132],"WER":[133],"reductions":[134],"words.":[138],"highly":[141],"efficient:":[142],"it":[143],"can":[144],"handle":[145],"5,000":[146],"distractors":[150],"only":[152],"add":[153],"small":[155],"overhead":[156],"memory":[158],"use":[159],"computation":[161],"cost.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}