{"id":"https://openalex.org/W3007905516","doi":"https://doi.org/10.1109/asru46091.2019.9003837","title":"Integrating Source-Channel and Attention-Based Sequence-to-Sequence Models for Speech Recognition","display_name":"Integrating Source-Channel and Attention-Based Sequence-to-Sequence Models for Speech Recognition","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007905516","doi":"https://doi.org/10.1109/asru46091.2019.9003837","mag":"3007905516"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003837","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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/A5030757951","display_name":"Qiujia Li","orcid":"https://orcid.org/0000-0003-3074-3692"},"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":true,"raw_author_name":"Qiujia Li","raw_affiliation_strings":["Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ","Engineering Dept., Cambridge University, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Engineering Dept., Cambridge University, Cambridge, U.K","institution_ids":[]}]},{"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","Engineering Dept., Cambridge University, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Engineering Dept., Cambridge University, Cambridge, U.K","institution_ids":[]}]},{"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","Engineering Dept., Cambridge University, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Engineering Dept., Cambridge University, Cambridge, U.K","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5030757951"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":1.8202,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.89367577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"46"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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":0.8376255631446838},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6274005174636841},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6175971031188965},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6033070683479309},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5884519815444946},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5573524236679077},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5435779094696045},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.49257832765579224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4885922074317932},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4724348485469818},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.4636472463607788},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.4631834030151367},{"id":"https://openalex.org/keywords/complementarity","display_name":"Complementarity (molecular biology)","score":0.42952144145965576},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3867587149143219},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2533041536808014},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1778758466243744},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.09518182277679443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8376255631446838},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6274005174636841},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6175971031188965},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6033070683479309},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5884519815444946},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5573524236679077},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5435779094696045},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.49257832765579224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4885922074317932},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4724348485469818},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.4636472463607788},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.4631834030151367},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.42952144145965576},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3867587149143219},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2533041536808014},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1778758466243744},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.09518182277679443},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003837","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":90,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W86969866","https://openalex.org/W173561343","https://openalex.org/W854541894","https://openalex.org/W1489125746","https://openalex.org/W1508165687","https://openalex.org/W1533416326","https://openalex.org/W1828163288","https://openalex.org/W1904457459","https://openalex.org/W1942035323","https://openalex.org/W1987238397","https://openalex.org/W2002342963","https://openalex.org/W2003123121","https://openalex.org/W2007857129","https://openalex.org/W2079623482","https://openalex.org/W2112036188","https://openalex.org/W2125336414","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2147768505","https://openalex.org/W2150907703","https://openalex.org/W2158069733","https://openalex.org/W2160815625","https://openalex.org/W2183341477","https://openalex.org/W2184045248","https://openalex.org/W2327501763","https://openalex.org/W2345190899","https://openalex.org/W2396384435","https://openalex.org/W2402146185","https://openalex.org/W2514741789","https://openalex.org/W2515439472","https://openalex.org/W2521999726","https://openalex.org/W2526425061","https://openalex.org/W2530486890","https://openalex.org/W2530876040","https://openalex.org/W2608712415","https://openalex.org/W2747135936","https://openalex.org/W2748816379","https://openalex.org/W2759071281","https://openalex.org/W2766219058","https://openalex.org/W2883586237","https://openalex.org/W2886180730","https://openalex.org/W2889282842","https://openalex.org/W2889374926","https://openalex.org/W2891980359","https://openalex.org/W2892009249","https://openalex.org/W2892124901","https://openalex.org/W2899879954","https://openalex.org/W2913041008","https://openalex.org/W2936706905","https://openalex.org/W2936774411","https://openalex.org/W2938372602","https://openalex.org/W2939111082","https://openalex.org/W2944255943","https://openalex.org/W2952288254","https://openalex.org/W2962778134","https://openalex.org/W2962780374","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2962940707","https://openalex.org/W2963144852","https://openalex.org/W2963362078","https://openalex.org/W2963403664","https://openalex.org/W2963654251","https://openalex.org/W2963727906","https://openalex.org/W2963742216","https://openalex.org/W2963747784","https://openalex.org/W2963920996","https://openalex.org/W2964107261","https://openalex.org/W2964272710","https://openalex.org/W2964308564","https://openalex.org/W2972451902","https://openalex.org/W3103005696","https://openalex.org/W3149335959","https://openalex.org/W4289440825","https://openalex.org/W4294619417","https://openalex.org/W6607114211","https://openalex.org/W6623517193","https://openalex.org/W6629052376","https://openalex.org/W6638749077","https://openalex.org/W6640708543","https://openalex.org/W6678809451","https://openalex.org/W6679434410","https://openalex.org/W6712930963","https://openalex.org/W6728811460","https://openalex.org/W6747158283","https://openalex.org/W6752739165","https://openalex.org/W6753742271","https://openalex.org/W6754576867","https://openalex.org/W7027429494"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W2151348424","https://openalex.org/W2594897229","https://openalex.org/W4290708361","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W2129812225","https://openalex.org/W1507733787","https://openalex.org/W2155620340"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,59,64,78,133],"novel":[4],"automatic":[5],"speech":[6],"recognition":[7],"(ASR)":[8],"framework":[9,42],"called":[10],"Integrated":[11],"Source-Channel":[12],"and":[13,30,47,58,146,158],"Attention":[14],"(ISCA)":[15],"that":[16,127],"combines":[17],"the":[18,25,67,74,83,109,114,117,122],"advantages":[19],"of":[20,116],"traditional":[21,39,87],"systems":[22,33,88,92],"based":[23,52,62,93],"on":[24,63,94,121],"noisy":[26,97],"source-channel":[27,98],"model":[28,111],"(SC)":[29],"end-to-end":[31,68,90],"style":[32,69,91],"using":[34,89],"attention-based":[35,70,118,159],"sequence-to-sequence":[36],"models.":[37,160],"The":[38],"SC":[40],"system":[41,71],"includes":[43],"hidden":[44],"Markov":[45],"models":[46,56,73],"connectionist":[48],"temporal":[49],"classification":[50],"(CTC)":[51],"acoustic":[53],"models,":[54],"language":[55],"(LMs),":[57],"decoding":[60],"procedure":[61],"lexicon,":[65],"whereas":[66],"jointly":[72],"whole":[75],"process":[76],"with":[77],"single":[79],"model.":[80,119],"By":[81],"rescoring":[82],"hypotheses":[84],"produced":[85],"by":[86,147],"an":[95,143,150],"extended":[96],"model,":[99],"ISCA":[100,128],"allows":[101],"structured":[102],"knowledge":[103],"to":[104,131,140],"be":[105],"easily":[106],"incorporated":[107],"via":[108],"SC-based":[110],"while":[112],"exploiting":[113],"complementarity":[115],"Experiments":[120],"AMI":[123],"meeting":[124],"corpus":[125],"show":[126],"is":[129],"able":[130],"give":[132],"relative":[134],"word":[135],"error":[136],"rate":[137],"reduction":[138],"up":[139],"21%":[141],"over":[142,149],"individual":[144],"system,":[145],"13%":[148],"alternative":[151],"method":[152],"which":[153],"also":[154],"involves":[155],"combining":[156],"CTC":[157]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}