{"id":"https://openalex.org/W2886025712","doi":"https://doi.org/10.1109/slt.2018.8639044","title":"Dialog-Context Aware end-to-end Speech Recognition","display_name":"Dialog-Context Aware end-to-end Speech Recognition","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2886025712","doi":"https://doi.org/10.1109/slt.2018.8639044","mag":"2886025712"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5062940343","display_name":"Suyoun Kim","orcid":"https://orcid.org/0000-0002-6822-337X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suyoun Kim","raw_affiliation_strings":["Electrical & Computer Engineering, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical & Computer Engineering, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.3768,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.92082288,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"2018","issue":null,"first_page":"434","last_page":"440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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/dialog-box","display_name":"Dialog box","score":0.9037191867828369},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8631011843681335},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6712365746498108},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6637553572654724},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6629245281219482},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6377147436141968},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.572909951210022},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.5193203687667847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5083693861961365},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4622926414012909},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.06861665844917297}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.9037191867828369},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8631011843681335},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6712365746498108},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6637553572654724},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6629245281219482},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6377147436141968},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.572909951210022},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.5193203687667847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5083693861961365},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4622926414012909},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.06861665844917297},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt.2018.8639044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"mag:3088248897","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=201902281660172494","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W179875071","https://openalex.org/W854541894","https://openalex.org/W1586532344","https://openalex.org/W1815076433","https://openalex.org/W1855892484","https://openalex.org/W1880262756","https://openalex.org/W1922655562","https://openalex.org/W1999965501","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2166637769","https://openalex.org/W2197913429","https://openalex.org/W2207587218","https://openalex.org/W2519224033","https://openalex.org/W2521999726","https://openalex.org/W2526425061","https://openalex.org/W2530876040","https://openalex.org/W2573537087","https://openalex.org/W2627092829","https://openalex.org/W2766219058","https://openalex.org/W2962780374","https://openalex.org/W2962826786","https://openalex.org/W2963070863","https://openalex.org/W2963211739","https://openalex.org/W2963537349","https://openalex.org/W2964308564","https://openalex.org/W4231510805","https://openalex.org/W6600284362","https://openalex.org/W6607333740","https://openalex.org/W6623517193","https://openalex.org/W6635078382","https://openalex.org/W6638545294","https://openalex.org/W6639156005","https://openalex.org/W6639619044","https://openalex.org/W6640090968","https://openalex.org/W6675365184","https://openalex.org/W6676562027","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6687380338","https://openalex.org/W6688024653","https://openalex.org/W6739366949","https://openalex.org/W6743111917","https://openalex.org/W6746497681"],"related_works":["https://openalex.org/W48079147","https://openalex.org/W2394821827","https://openalex.org/W326836678","https://openalex.org/W2563921006","https://openalex.org/W1963944933","https://openalex.org/W2111550420","https://openalex.org/W1977846844","https://openalex.org/W2549666521","https://openalex.org/W3133893348","https://openalex.org/W2901575119"],"abstract_inverted_index":{"Existing":[0],"speech":[1,39,91,139,151],"recognition":[2,40,80,92,152],"systems":[3,41],"are":[4],"typically":[5],"built":[6],"at":[7],"the":[8,29,75,117,136],"sentence":[9],"level,":[10],"although":[11],"it":[12],"is":[13,57],"known":[14],"that":[15,21,64,116,143],"dialog":[16,66],"context,":[17],"e.g.":[18],"higher-level":[19],"knowledge":[20],"spans":[22],"across":[23],"sentences":[24],"or":[25],"speakers,":[26],"can":[27,120],"help":[28],"processing":[30],"of":[31,112],"long":[32],"conversations.":[33],"The":[34],"recent":[35],"progress":[36],"in":[37,102,126],"end-to-end":[38,76,104,128,150],"promises":[42],"to":[43,78],"integrate":[44],"all":[45],"available":[46],"information":[47,68,98,125],"(e.g.":[48],"acoustic,":[49],"language":[50],"resources)":[51],"into":[52,74],"a":[53,88,110,147],"single":[54],"model,":[55,93],"which":[56,94],"then":[58],"jointly":[59],"optimized.":[60],"It":[61],"seems":[62],"natural":[63],"such":[65],"context":[67,97],"should":[69],"thus":[70],"also":[71],"be":[72,121],"integrated":[73],"models":[77],"improve":[79],"accuracy":[81],"further.":[82],"In":[83],"this":[84],"work,":[85],"we":[86],"present":[87],"dialog-context":[89,107,124],"aware":[90],"explicitly":[95],"uses":[96],"beyond":[99],"sentence-level":[100,113,149],"information,":[101],"an":[103,127],"fashion.":[105],"Our":[106],"model":[108],"captures":[109],"history":[111],"contexts,":[114],"so":[115],"whole":[118],"system":[119,145],"trained":[122],"with":[123],"manner.":[129],"We":[130],"evaluate":[131],"our":[132,144],"proposed":[133],"approach":[134],"on":[135],"Switchboard":[137],"conversational":[138],"corpus,":[140],"and":[141],"show":[142],"outperforms":[146],"comparable":[148],"system.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}