{"id":"https://openalex.org/W2894835365","doi":"https://doi.org/10.1109/slt.2018.8639655","title":"Multilingual Sequence-to-Sequence Speech Recognition: Architecture, Transfer Learning, and Language Modeling","display_name":"Multilingual Sequence-to-Sequence Speech Recognition: Architecture, Transfer Learning, and Language Modeling","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2894835365","doi":"https://doi.org/10.1109/slt.2018.8639655","mag":"2894835365"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639655","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":"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/A5059500729","display_name":"Jaejin Cho","orcid":"https://orcid.org/0000-0001-5672-6765"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jaejin Cho","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064113992","display_name":"Murali Karthick Baskar","orcid":"https://orcid.org/0000-0002-9396-6319"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Murali Karthick Baskar","raw_affiliation_strings":["Brno University of Technology"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760516","display_name":"Ruizhi Li","orcid":"https://orcid.org/0000-0002-2496-5224"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruizhi Li","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014455067","display_name":"Matthew Wiesner","orcid":"https://orcid.org/0000-0001-8653-7738"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Wiesner","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047596805","display_name":"Sri Harish Mallidi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sri Harish Mallidi","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112575316","display_name":"Nelson Yalta","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nelson Yalta","raw_affiliation_strings":["Waseda University"],"affiliations":[{"raw_affiliation_string":"Waseda University","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065253688","display_name":"Martin Karafi\u00e1t","orcid":"https://orcid.org/0000-0001-6474-8366"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Martin Karafiat","raw_affiliation_strings":["Brno University of Technology"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL)"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL)","institution_ids":["https://openalex.org/I4210133125"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5059500729"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":10.2617,"has_fulltext":false,"cited_by_count":112,"citation_normalized_percentile":{"value":0.98464306,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"521","last_page":"527"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9965999722480774,"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":0.8618078231811523},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6524743437767029},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6446411609649658},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6149137616157532},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5654412508010864},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5400053262710571},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5365801453590393},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5082242488861084},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5024309158325195},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48811444640159607},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4243202209472656},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4111191928386688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8618078231811523},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6524743437767029},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6446411609649658},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6149137616157532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5654412508010864},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5400053262710571},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5365801453590393},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5082242488861084},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5024309158325195},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48811444640159607},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4243202209472656},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4111191928386688},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2018.8639655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639655","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W950853366","https://openalex.org/W1524333225","https://openalex.org/W1686810756","https://openalex.org/W2038810952","https://openalex.org/W2064675550","https://openalex.org/W2091746061","https://openalex.org/W2094147890","https://openalex.org/W2096140469","https://openalex.org/W2102113734","https://openalex.org/W2130942839","https://openalex.org/W2131774270","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2327501763","https://openalex.org/W2474824677","https://openalex.org/W2586412610","https://openalex.org/W2627092829","https://openalex.org/W2633221078","https://openalex.org/W2697044473","https://openalex.org/W2743818757","https://openalex.org/W2766219058","https://openalex.org/W2769437540","https://openalex.org/W2786835190","https://openalex.org/W2962780374","https://openalex.org/W2963292011","https://openalex.org/W2963403664","https://openalex.org/W2964089206","https://openalex.org/W2964272710","https://openalex.org/W2964308564","https://openalex.org/W2964309797","https://openalex.org/W4294619417","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6720877245","https://openalex.org/W6739324457","https://openalex.org/W6739366949","https://openalex.org/W6746041127","https://openalex.org/W6747158283"],"related_works":["https://openalex.org/W2021413527","https://openalex.org/W2058877998","https://openalex.org/W2963920996","https://openalex.org/W1489125746","https://openalex.org/W2592040118","https://openalex.org/W4297665160","https://openalex.org/W2896411932","https://openalex.org/W2136869290","https://openalex.org/W1586532344","https://openalex.org/W4205868073"],"abstract_inverted_index":{"Sequence-to-sequence":[0],"(seq2seq)":[1],"approach":[2,15,116],"for":[3,81],"low-resource":[4],"ASR":[5],"is":[6],"a":[7,29,55,60,96,104],"relatively":[8],"new":[9,30],"direction":[10],"in":[11,139],"speech":[12],"research.":[13],"The":[14,88],"benefits":[16],"by":[17],"performing":[18],"model":[19,58,101,106,120],"training":[20,155],"without":[21],"using":[22,72],"lexicon":[23],"and":[24,63,143],"alignments.":[25],"However,":[26],"this":[27,42],"poses":[28],"problem":[31],"of":[32,94,141],"requiring":[33],"more":[34,154],"data":[35,48],"compared":[36],"to":[37,46,53,148],"conventional":[38],"DNN-HMM":[39],"systems.":[40],"In":[41],"work,":[43],"we":[44],"attempt":[45],"use":[47],"from":[49,117],"10":[50],"BABEL":[51,70,130],"languages":[52,71],"build":[54],"multilingual":[56,85,119],"seq2seq":[57,86,105],"as":[59],"prior":[61,84],"model,":[62],"then":[64],"port":[65],"them":[66],"towards":[67],"4":[68,129],"other":[69],"transfer":[73,114],"learning":[74,115],"approach.":[75],"We":[76],"also":[77,90,135],"explore":[78],"different":[79],"architectures":[80],"improving":[82],"the":[83,92,113,118,149],"model.":[87],"paper":[89],"discusses":[91],"effect":[93],"integrating":[95],"recurrent":[97],"neural":[98],"network":[99],"language":[100],"(RNNLM)":[102],"with":[103,152],"during":[107],"decoding.":[108],"Experimental":[109],"results":[110],"show":[111],"that":[112],"shows":[121],"substantial":[122],"gains":[123],"over":[124],"monolingual":[125],"models":[126,150],"across":[127],"all":[128],"languages.":[131],"Incorporating":[132],"an":[133],"RNNLM":[134],"brings":[136],"significant":[137],"improvements":[138],"terms":[140],"%WER,":[142],"achieves":[144],"recognition":[145],"performance":[146],"comparable":[147],"trained":[151],"twice":[153],"data.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":12}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}