{"id":"https://openalex.org/W2900169601","doi":"https://doi.org/10.21437/interspeech.2019-2355","title":"Analysis of Multilingual Sequence-to-Sequence Speech Recognition Systems","display_name":"Analysis of Multilingual Sequence-to-Sequence Speech Recognition Systems","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2900169601","doi":"https://doi.org/10.21437/interspeech.2019-2355","mag":"2900169601"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2355","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.03451","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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 Karafi\u00e1t","raw_affiliation_strings":["Brno University of Technology;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology;","institution_ids":["https://openalex.org/I60587646"]}]},{"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;"],"raw_orcid":null,"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["Mitsubishi Electric Research USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083952536","display_name":"Jan Honza'' \u010cernock\u00fdBrno University of Technology","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan \u010cernock\u00fd","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6561,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73639399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2220","last_page":"2224"},"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":0.9994000196456909,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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":0.8105639815330505},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8094749450683594},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6025131940841675},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5747998952865601},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5739647746086121},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5290963649749756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.524027407169342},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.49561965465545654},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4776976406574249},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47455817461013794},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.465002179145813},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11683374643325806},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06776052713394165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8105639815330505},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8094749450683594},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6025131940841675},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5747998952865601},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5739647746086121},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5290963649749756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.524027407169342},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.49561965465545654},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4776976406574249},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47455817461013794},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.465002179145813},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11683374643325806},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06776052713394165},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2019-2355","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1811.03451","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.03451","pdf_url":"https://arxiv.org/pdf/1811.03451","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.1811.03451","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1811.03451","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2900169601","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.03451","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.03451","pdf_url":"https://arxiv.org/pdf/1811.03451","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2900169601.pdf","grobid_xml":"https://content.openalex.org/works/W2900169601.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2102113734","https://openalex.org/W2950635152","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2972347614","https://openalex.org/W2951816288","https://openalex.org/W2748679025","https://openalex.org/W2901254300","https://openalex.org/W2901739041","https://openalex.org/W2891816510","https://openalex.org/W2963292011","https://openalex.org/W2799316004","https://openalex.org/W2950903920","https://openalex.org/W1992912377","https://openalex.org/W2395465351","https://openalex.org/W3129905227","https://openalex.org/W2769639994","https://openalex.org/W2743818757","https://openalex.org/W2587496545","https://openalex.org/W3025712427","https://openalex.org/W2964309797","https://openalex.org/W3197163313","https://openalex.org/W2920970185","https://openalex.org/W3104842308"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,34,73,85,92,115,118,122],"applications":[4],"of":[5,28,36,52,62,75,117],"various":[6,47],"multilingual":[7,100,104,127],"approaches":[8],"developed":[9],"in":[10,78,91],"conventional":[11],"hidden":[12],"Markov":[13],"model":[14],"(HMM)":[15],"systems":[16],"to":[17,103],"sequence-to-sequence":[18],"(seq2seq)":[19],"automatic":[20],"speech":[21],"recognition":[22],"(ASR).":[23],"On":[24],"a":[25,79],"set":[26],"composed":[27],"Babel":[29],"data,":[30],"we":[31,45,98,111],"first":[32],"show":[33],"effectiveness":[35,74],"multi-lingual":[37,53,94],"training":[38,50,95],"with":[39,121],"stacked":[40],"bottle-neck":[41],"(SBN)":[42],"features.":[43],"Then":[44],"explore":[46],"architectures":[48],"and":[49,106],"strategies":[51],"seq2seq":[54,123],"models":[55],"based":[56],"on":[57],"CTC-attention":[58],"networks":[59],"including":[60],"combinations":[61],"output":[63],"layer,":[64],"CTC":[65],"and/or":[66],"attention":[67],"component":[68],"re-training.":[69],"We":[70],"also":[71],"investigate":[72],"language-transfer":[76],"learning":[77],"very":[80],"low":[81],"resource":[82],"scenario":[83],"when":[84],"target":[86],"language":[87],"is":[88],"not":[89],"included":[90],"original":[93],"data.":[96],"Interestingly,":[97],"found":[99],"features":[101],"superior":[102],"models,":[105],"this":[107],"finding":[108],"suggests":[109],"that":[110],"can":[112],"efficiently":[113],"combine":[114],"benefits":[116],"HMM":[119],"system":[120,124],"through":[125],"these":[126],"feature":[128],"techniques.":[129]},"counts_by_year":[{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}