{"id":"https://openalex.org/W2962893195","doi":"https://doi.org/10.1109/icassp.2018.8461886","title":"Multi-Dialect Speech Recognition with a Single Sequence-to-Sequence Model","display_name":"Multi-Dialect Speech Recognition with a Single Sequence-to-Sequence Model","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2962893195","doi":"https://doi.org/10.1109/icassp.2018.8461886","mag":"2962893195"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100374448","display_name":"Bo Li","orcid":"https://orcid.org/0000-0002-6711-3603"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032798707","display_name":"Khe Chai Sim","orcid":"https://orcid.org/0000-0002-0866-2223"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khe Chai Sim","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049614700","display_name":"Michiel Bacchiani","orcid":"https://orcid.org/0000-0003-4527-0197"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michiel Bacchiani","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058585526","display_name":"Eugene Weinstein","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Weinstein","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111455517","display_name":"Patrick Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Nguyen","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100715424","display_name":"Zhifeng Chen","orcid":"https://orcid.org/0000-0001-8631-2424"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhifeng Chen","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081310561","display_name":"Yanghui Wu","orcid":"https://orcid.org/0000-0002-5950-9747"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanghui Wu","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111514705","display_name":"Kanishka Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kanishka Rao","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":117,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4749","last_page":"4753"},"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":0.9990000128746033,"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":0.996999979019165,"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/grapheme","display_name":"Grapheme","score":0.7998597621917725},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7450833320617676},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7325193285942078},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.7206586599349976},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5763955116271973},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.55059814453125},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5259675979614258},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5033530592918396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48198121786117554},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4804341793060303},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4338851869106293},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42418766021728516},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.322005033493042},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08928865194320679}],"concepts":[{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.7998597621917725},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7450833320617676},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7325193285942078},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7206586599349976},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5763955116271973},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.55059814453125},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5259675979614258},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5033530592918396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48198121786117554},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4804341793060303},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4338851869106293},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42418766021728516},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.322005033493042},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08928865194320679},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1489125746","https://openalex.org/W1528577938","https://openalex.org/W1537735731","https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W1978660892","https://openalex.org/W1993409002","https://openalex.org/W1994606281","https://openalex.org/W2045070791","https://openalex.org/W2064675550","https://openalex.org/W2094035326","https://openalex.org/W2102113734","https://openalex.org/W2106440210","https://openalex.org/W2130414229","https://openalex.org/W2155770957","https://openalex.org/W2161106747","https://openalex.org/W2167949757","https://openalex.org/W2168231600","https://openalex.org/W2271840356","https://openalex.org/W2276408190","https://openalex.org/W2294108103","https://openalex.org/W2407897255","https://openalex.org/W2515439472","https://openalex.org/W2530876040","https://openalex.org/W2550821151","https://openalex.org/W2587080466","https://openalex.org/W2603679025","https://openalex.org/W2608712415","https://openalex.org/W2617258110","https://openalex.org/W2750499125","https://openalex.org/W2786835190","https://openalex.org/W2893449927","https://openalex.org/W2963882470","https://openalex.org/W6623517193","https://openalex.org/W6631740672","https://openalex.org/W6639156005","https://openalex.org/W6649207683","https://openalex.org/W6673792607","https://openalex.org/W6675365184","https://openalex.org/W6683679900","https://openalex.org/W6696757691","https://openalex.org/W6728892627","https://openalex.org/W6737292097","https://openalex.org/W6745731079","https://openalex.org/W6748640972"],"related_works":["https://openalex.org/W2506515307","https://openalex.org/W4385893898","https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2060656088","https://openalex.org/W2335200603","https://openalex.org/W2900413183","https://openalex.org/W2183593636","https://openalex.org/W2080578089","https://openalex.org/W2179005426"],"abstract_inverted_index":{"Sequence-to-sequence":[0],"models":[1,29],"provide":[2],"a":[3,18,31,58,105,143,174,179],"simple":[4],"and":[5,26,48,52,81,140],"elegant":[6],"solution":[7],"for":[8,77,83],"building":[9],"speech":[10],"recognition":[11],"systems":[12,73],"by":[13,122,127,190],"folding":[14],"separate":[15,78],"components":[16],"of":[17,56,70,104,135,146,153,186],"typical":[19],"system,":[20],"namely":[21,45],"acoustic":[22],"(AM),":[23],"pronunciation":[24],"(PM)":[25],"language":[27],"(LM)":[28],"into":[30,96,118,150],"single":[32,59,175],"neural":[33],"network.":[34],"In":[35],"this":[36],"work,":[37],"we":[38],"look":[39,113],"at":[40,114,132],"one":[41,97],"such":[42],"sequence-to-sequence":[43],"model,":[44,120,177],"listen,":[46],"attend":[47],"spell":[49],"(LAS)":[50],"[1],":[51],"explore":[53],"the":[54,68,75,91,102,119,124,129,133,136,147,154,187],"possibility":[55],"training":[57,71,125],"model":[60,99,106,181],"to":[61],"serve":[62],"different":[63],"English":[64,160],"dialects,":[65],"which":[66],"simplifies":[67],"process":[69],"multi-dialect":[72],"without":[74],"need":[76],"AM,":[79],"PM":[80],"LMs":[82],"each":[84,109,185],"dialect.":[85,110],"We":[86,111],"show":[87,162],"that":[88,163],"simply":[89],"pooling":[90],"data":[92],"from":[93],"all":[94,151],"dialects":[95,161,189],"LAS":[98,176,180],"falls":[100],"behind":[101],"performance":[103],"fine-tuned":[107],"on":[108,158,184],"then":[112],"incorporating":[115],"dialect-specific":[116],"information":[117,149],"both":[121],"modifying":[123],"targets":[126],"inserting":[128],"dialect":[130,148,171],"symbol":[131],"end":[134],"original":[137],"grapheme":[138],"sequence":[139],"also":[141],"feeding":[142],"1-hot":[144],"representation":[145],"layers":[152],"model.":[155],"Experimental":[156],"results":[157],"seven":[159,188],"our":[164],"proposed":[165],"system":[166],"is":[167],"effective":[168],"in":[169],"modeling":[170],"variations":[172],"within":[173],"outperforming":[178],"trained":[182],"individually":[183],"3.1~16.5%":[191],"relative.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":26},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}