{"id":"https://openalex.org/W4311187265","doi":"https://doi.org/10.1109/taslp.2022.3224286","title":"Minimising Biasing Word Errors for Contextual ASR With the Tree-Constrained Pointer Generator","display_name":"Minimising Biasing Word Errors for Contextual ASR With the Tree-Constrained Pointer Generator","publication_year":2022,"publication_date":"2022-11-24","ids":{"openalex":"https://openalex.org/W4311187265","doi":"https://doi.org/10.1109/taslp.2022.3224286"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3224286","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3224286","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/09961919.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/09961919.pdf","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":["Department of Engineering, University of Cambridge, Cambridge, U.K"],"raw_orcid":"https://orcid.org/0000-0002-5886-056X","affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, U.K","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/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7730-5131","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"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":["Department of Engineering, University of Cambridge, Cambridge, U.K"],"raw_orcid":"https://orcid.org/0000-0001-9069-0225","affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0497,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80826184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"31","issue":null,"first_page":"345","last_page":"354"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9997000098228455,"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":0.7468950748443604},{"id":"https://openalex.org/keywords/biasing","display_name":"Biasing","score":0.599093496799469},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5474144220352173},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.512437641620636},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5045231580734253},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.4161643981933594},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.41387268900871277},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4116593301296234},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3255031704902649},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32045674324035645},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.14580976963043213},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11756500601768494}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7468950748443604},{"id":"https://openalex.org/C20254490","wikidata":"https://www.wikidata.org/wiki/Q719550","display_name":"Biasing","level":3,"score":0.599093496799469},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5474144220352173},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.512437641620636},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5045231580734253},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.4161643981933594},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.41387268900871277},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4116593301296234},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3255031704902649},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32045674324035645},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.14580976963043213},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11756500601768494},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3224286","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3224286","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/09961919.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2022.3224286","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3224286","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/09961919.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4311187265.pdf","grobid_xml":"https://content.openalex.org/works/W4311187265.grobid-xml"},"referenced_works_count":72,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1686810756","https://openalex.org/W1942035323","https://openalex.org/W2003123121","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2150907703","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/W2883586237","https://openalex.org/W2886180730","https://openalex.org/W2886319145","https://openalex.org/W2889012072","https://openalex.org/W2889163603","https://openalex.org/W2889282842","https://openalex.org/W2892124901","https://openalex.org/W2898599211","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/W2963747784","https://openalex.org/W2963827914","https://openalex.org/W2972625221","https://openalex.org/W2973172693","https://openalex.org/W2992739892","https://openalex.org/W3005302685","https://openalex.org/W3007227084","https://openalex.org/W3007905516","https://openalex.org/W3008037978","https://openalex.org/W3008174054","https://openalex.org/W3008323921","https://openalex.org/W3015470971","https://openalex.org/W3015686596","https://openalex.org/W3016234571","https://openalex.org/W3022882149","https://openalex.org/W3042416212","https://openalex.org/W3094979069","https://openalex.org/W3095697114","https://openalex.org/W3095962459","https://openalex.org/W3096758108","https://openalex.org/W3097239815","https://openalex.org/W3097777922","https://openalex.org/W3097794466","https://openalex.org/W3140235797","https://openalex.org/W3152221657","https://openalex.org/W3162639446","https://openalex.org/W3163560333","https://openalex.org/W3184976814","https://openalex.org/W3185108477","https://openalex.org/W3198004110","https://openalex.org/W3206876927","https://openalex.org/W4221151615","https://openalex.org/W4226292626","https://openalex.org/W4226462878","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6637373629","https://openalex.org/W6682398751","https://openalex.org/W6739901393","https://openalex.org/W6777472801","https://openalex.org/W6802906506"],"related_works":["https://openalex.org/W3196321793","https://openalex.org/W3080705045","https://openalex.org/W2142481367","https://openalex.org/W2385527937","https://openalex.org/W2005880840","https://openalex.org/W3173108628","https://openalex.org/W2035645574","https://openalex.org/W1005360155","https://openalex.org/W2944691285","https://openalex.org/W168676510"],"abstract_inverted_index":{"Contextual":[0],"knowledge":[1],"is":[2],"essential":[3],"for":[4],"reducing":[5],"speech":[6],"recognition":[7,80,175],"errors":[8,104],"on":[9,125,164,193,214],"high-valued":[10],"long-tail":[11,34],"words.":[12,84,196],"This":[13],"paper":[14],"proposes":[15],"a":[16,31,43,61,66,91,109],"novel":[17,92],"tree-constrained":[18],"pointer":[19],"generator":[20],"(TCPGen)":[21],"component":[22],"that":[23,99],"enables":[24],"end-to-end":[25],"ASR":[26,75,121],"models":[27],"to":[28,77],"bias":[29],"towards":[30],"list":[32],"of":[33,56,81,185,202],"words":[35,58,167,203,217],"obtained":[36],"using":[37],"external":[38],"contextual":[39,120],"information.":[40],"With":[41],"only":[42],"small":[44],"overhead":[45],"in":[46,173,205,218],"memory":[47],"use":[48],"and":[49,64,72,131,179,187],"computation":[50],"cost,":[51],"TCPGen":[52,197],"can":[53],"structure":[54],"thousands":[55],"biasing":[57,83,94,102,143,166,195,220],"efficiently":[59],"into":[60],"symbolic":[62],"prefix-tree,":[63],"creates":[65],"neural":[67],"shortcut":[68],"between":[69],"the":[70,73,79,82,117,126,132,135,142,147,165,174,183,194,206,215,219],"tree":[71],"final":[74],"output":[76],"facilitate":[78],"To":[85],"enhance":[86],"TCPGen,":[87,159,186],"we":[88],"further":[89,181],"propose":[90],"minimum":[93],"word":[95,103,151],"error":[96,152,176],"(MBWE)":[97],"loss":[98],"directly":[100],"optimises":[101],"during":[105,116],"training,":[106],"along":[107],"with":[108,141,158,168,210],"biasing-word-driven":[110],"language":[111],"model":[112],"discounting":[113],"(BLMD)":[114],"method":[115],"test.":[118],"All":[119],"systems":[122],"were":[123,156,161],"evaluated":[124],"public":[127],"Librispeech":[128],"audiobook":[129],"corpus":[130],"data":[133],"from":[134,146],"dialogue":[136],"state":[137],"tracking":[138],"challenges":[139],"(DSTC)":[140],"lists":[144],"extracted":[145],"dialogue-system":[148],"ontology.":[149],"Consistent":[150],"rate":[153],"(WER)":[154],"reductions":[155,172,192,213],"achieved":[157,188,199],"which":[160],"particularly":[162],"significant":[163,190],"around":[169],"40%":[170],"relative":[171],"rates.":[177],"MBWE":[178],"BLMD":[180],"improved":[182],"effectiveness":[184],"more":[189],"WER":[191,212],"also":[198],"zero-shot":[200],"learning":[201],"not":[204],"audio":[207],"training":[208],"set":[209],"large":[211],"out-of-vocabulary":[216],"list.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}