{"id":"https://openalex.org/W4283832239","doi":"https://doi.org/10.21437/interspeech.2022-461","title":"Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition","display_name":"Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283832239","doi":"https://doi.org/10.21437/interspeech.2022-461"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-461","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-461","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":true,"raw_author_name":"Guangzhi Sun","raw_affiliation_strings":["Cambridge University Engineering Dept., Trumpington St., Cambridge, CB2 1PZ U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept., Trumpington St., Cambridge, CB2 1PZ U.K","institution_ids":["https://openalex.org/I4210096386","https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460272","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0003-3009-598X"},"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"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Cambridge University Engineering Dept., Trumpington St., Cambridge, CB2 1PZ U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept., Trumpington St., Cambridge, CB2 1PZ U.K","institution_ids":["https://openalex.org/I4210096386","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"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":false,"raw_author_name":"Phil Woodland","raw_affiliation_strings":["Cambridge University Engineering Dept., Trumpington St., Cambridge, CB2 1PZ U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept., Trumpington St., Cambridge, CB2 1PZ U.K","institution_ids":["https://openalex.org/I4210096386","https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077772423"],"corresponding_institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210096386"],"apc_list":null,"apc_paid":null,"fwci":0.835,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73784915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2043","last_page":"2047"},"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":0.9995999932289124,"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":0.9976000189781189,"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":0.8493430614471436},{"id":"https://openalex.org/keywords/pointer","display_name":"Pointer (user interface)","score":0.7708406448364258},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.494274377822876},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4545747637748718},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4141535758972168},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3856317698955536},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3810047507286072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3657541871070862},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.20208555459976196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8493430614471436},{"id":"https://openalex.org/C150202949","wikidata":"https://www.wikidata.org/wiki/Q107602","display_name":"Pointer (user interface)","level":2,"score":0.7708406448364258},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.494274377822876},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4545747637748718},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4141535758972168},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3856317698955536},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3810047507286072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3657541871070862},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.20208555459976196},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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:10.21437/interspeech.2022-461","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-461","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2104518905","https://openalex.org/W2125336414","https://openalex.org/W2127827747","https://openalex.org/W2143612262","https://openalex.org/W2250644439","https://openalex.org/W2250877157","https://openalex.org/W2251012068","https://openalex.org/W2327501763","https://openalex.org/W2606974598","https://openalex.org/W2758765981","https://openalex.org/W2785128315","https://openalex.org/W2810084418","https://openalex.org/W2886319145","https://openalex.org/W2889012072","https://openalex.org/W2898599211","https://openalex.org/W2903250132","https://openalex.org/W2936774411","https://openalex.org/W2952198026","https://openalex.org/W2962780374","https://openalex.org/W2963922633","https://openalex.org/W2964015378","https://openalex.org/W2972625221","https://openalex.org/W2973172693","https://openalex.org/W2990474076","https://openalex.org/W3008037978","https://openalex.org/W3015747801","https://openalex.org/W3022882149","https://openalex.org/W3024172799","https://openalex.org/W3097239815","https://openalex.org/W3097777922","https://openalex.org/W3097794466","https://openalex.org/W3140235797","https://openalex.org/W4224920362","https://openalex.org/W4225289150","https://openalex.org/W4226292626","https://openalex.org/W4226462878","https://openalex.org/W4287240666","https://openalex.org/W4297733535","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W3017902212","https://openalex.org/W2964335273","https://openalex.org/W2982145560","https://openalex.org/W2969450769"],"abstract_inverted_index":{"Incorporating":[0],"biasing":[1,39,87,97,114,137],"words":[2,40,115,138],"obtained":[3],"as":[4],"contextual":[5,35,109],"knowledge":[6],"is":[7,56],"critical":[8],"for":[9,33,49,152],"many":[10],"automatic":[11],"speech":[12],"recognition":[13],"(ASR)":[14],"applications.This":[15],"paper":[16],"proposes":[17],"the":[18,38,42,69,82,86,92,101,136,141,149],"use":[19],"of":[20,81,85],"graph":[21],"neural":[22],"network":[23],"(GNN)":[24],"encodings":[25,126],"in":[26,41,52,148],"a":[27,45,77,106,129,145],"tree-constrained":[28],"pointer":[29],"generator":[30],"(TCP-Gen)":[31],"component":[32],"end-to-end":[34,53],"ASR.By":[36],"encoding":[37],"prefix-tree":[43],"with":[44,124,144],"tree-based":[46],"GNN,":[47],"lookahead":[48],"future":[50],"wordpieces":[51,67],"ASR":[54,110],"decoding":[55],"achieved":[57,127],"at":[58],"each":[59,119],"tree":[60,70],"node":[61],"by":[62,104],"incorporating":[63],"information":[64],"about":[65,128],"all":[66],"on":[68,91,100,135],"branches":[71],"rooted":[72],"from":[73,116],"it,":[74],"which":[75],"allows":[76],"more":[78],"accurate":[79],"prediction":[80],"generation":[83],"probability":[84],"words.Systems":[88],"were":[89],"evaluated":[90],"Librispeech":[93],"corpus":[94,103],"using":[95],"simulated":[96],"tasks,":[98],"and":[99],"AMI":[102],"proposing":[105],"novel":[107],"visual-grounded":[108],"pipeline":[111],"that":[112,122],"extracts":[113],"slides":[117],"alongside":[118],"meeting.Results":[120],"showed":[121],"TCPGen":[123],"GNN":[125],"further":[130],"15%":[131],"relative":[132],"WER":[133],"reduction":[134],"compared":[139],"to":[140],"original":[142],"TCPGen,":[143],"negligible":[146],"increase":[147],"computation":[150],"cost":[151],"decoding.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}