{"id":"https://openalex.org/W2962745521","doi":"https://doi.org/10.18653/v1/p19-1107","title":"Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion","display_name":"Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2962745521","doi":"https://doi.org/10.18653/v1/p19-1107","mag":"2962745521"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1107","pdf_url":"https://www.aclweb.org/anthology/P19-1107.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1107.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062940343","display_name":"Suyoun Kim","orcid":"https://orcid.org/0000-0002-6822-337X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Suyoun Kim","raw_affiliation_strings":["Electrical & Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Electrical & Computer Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068873086","display_name":"Siddharth Dalmia","orcid":"https://orcid.org/0000-0003-0437-5988"},"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"]},{"id":"https://openalex.org/I4210107233","display_name":"Language Science (South Korea)","ror":"https://ror.org/01h9v1373","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210107233"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Siddharth Dalmia","raw_affiliation_strings":["Language Technologies Institute, School of Computer Science Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, School of Computer Science Carnegie Mellon University","institution_ids":["https://openalex.org/I4210107233","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/I4210107233","display_name":"Language Science (South Korea)","ror":"https://ror.org/01h9v1373","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210107233"]},{"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":["KR","US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Language Technologies Institute, School of Computer Science Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, School of Computer Science Carnegie Mellon University","institution_ids":["https://openalex.org/I4210107233","https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062940343"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7225,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.7851239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1131","last_page":"1141"},"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/T10028","display_name":"Topic Modeling","score":0.9976999759674072,"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":0.9975000023841858,"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":0.8368761539459229},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7323055267333984},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7046763896942139},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6605355739593506},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6002256870269775},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5990124344825745},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5429707169532776},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5234465003013611},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5231886506080627},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4177738428115845},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4138530492782593},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11452049016952515}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8368761539459229},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7323055267333984},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7046763896942139},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6605355739593506},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6002256870269775},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5990124344825745},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5429707169532776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5234465003013611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5231886506080627},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4177738428115845},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4138530492782593},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11452049016952515},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1107","pdf_url":"https://www.aclweb.org/anthology/P19-1107.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1107","pdf_url":"https://www.aclweb.org/anthology/P19-1107.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2922803762","display_name":null,"funder_award_id":"45606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5921281487","display_name":null,"funder_award_id":"number","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7404166632","display_name":"Bridges: From Communities and Data to Workflows and Insight","funder_award_id":"1445606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8729765517","display_name":null,"funder_award_id":"ACI-1445606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962745521.pdf","grobid_xml":"https://content.openalex.org/works/W2962745521.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W179875071","https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1736701665","https://openalex.org/W1815076433","https://openalex.org/W1922655562","https://openalex.org/W1999965501","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/W2250539671","https://openalex.org/W2327501763","https://openalex.org/W2395416438","https://openalex.org/W2493916176","https://openalex.org/W2514741789","https://openalex.org/W2521999726","https://openalex.org/W2526425061","https://openalex.org/W2530876040","https://openalex.org/W2545177271","https://openalex.org/W2551396370","https://openalex.org/W2563351168","https://openalex.org/W2573537087","https://openalex.org/W2597757402","https://openalex.org/W2627092829","https://openalex.org/W2766219058","https://openalex.org/W2787560479","https://openalex.org/W2798881773","https://openalex.org/W2799800213","https://openalex.org/W2884975363","https://openalex.org/W2886025712","https://openalex.org/W2886319145","https://openalex.org/W2891176389","https://openalex.org/W2896457183","https://openalex.org/W2898599211","https://openalex.org/W2899771611","https://openalex.org/W2951529591","https://openalex.org/W2962704885","https://openalex.org/W2962739339","https://openalex.org/W2962780374","https://openalex.org/W2962826786","https://openalex.org/W2963070863","https://openalex.org/W2963211739","https://openalex.org/W2963341956","https://openalex.org/W2963626623","https://openalex.org/W2963970535","https://openalex.org/W2964308564","https://openalex.org/W3018009202"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W2375873920","https://openalex.org/W2146114872","https://openalex.org/W2392060890","https://openalex.org/W3196421258","https://openalex.org/W2944691285","https://openalex.org/W3193959417"],"abstract_inverted_index":{"We":[0,71],"present":[1],"a":[2,11],"novel":[3],"conversational-context":[4,28,69],"aware":[5],"end-to-end":[6,58,88],"speech":[7,21,79,89],"recognizer":[8],"based":[9],"on":[10,75],"gated":[12],"neural":[13],"network":[14],"that":[15,30,83],"incorporates":[16],"conversational-context/word/speech":[17],"embeddings.":[18],"Unlike":[19],"conventional":[20],"recognition":[22,90],"models,":[23],"our":[24,84],"model":[25,85],"learns":[26],"longer":[27],"information":[29],"spans":[31],"across":[32],"sentences":[33],"and":[34,81],"is":[35],"consequently":[36],"better":[37,68],"at":[38],"recognizing":[39],"long":[40],"conversations.":[41],"Specifically,":[42],"we":[43],"propose":[44],"to":[45],"use":[46],"text-based":[47],"external":[48],"word":[49,64],"and/or":[50],"sentence":[51],"embeddings":[52],"(i.e.,":[53],"fast-Text,":[54],"BERT)":[55],"within":[56],"an":[57],"framework,":[59],"yielding":[60],"significant":[61],"improvement":[62],"in":[63],"error":[65],"rate":[66],"with":[67],"representation.":[70],"evaluated":[72],"the":[73,76],"models":[74],"Switchboard":[77],"conversational":[78],"corpus":[80],"show":[82],"outperforms":[86],"standard":[87],"models.":[91]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}