{"id":"https://openalex.org/W2963336460","doi":"https://doi.org/10.1109/icassp.2018.8461614","title":"Multilingual Adaptation of RNN Based ASR Systems","display_name":"Multilingual Adaptation of RNN Based ASR Systems","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2963336460","doi":"https://doi.org/10.1109/icassp.2018.8461614","mag":"2963336460"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461614","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/A5035499291","display_name":"Markus Miiller","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Markus Miiller","raw_affiliation_strings":["Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055168905","display_name":"Sebastian Stiiker","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Stiiker","raw_affiliation_strings":["Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110453805","display_name":"Alex Waibel","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alex Waibel","raw_affiliation_strings":["Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":1.0186,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.82955344,"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":"5219","last_page":"5223"},"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9987000226974487,"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":0.836242139339447},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6968324184417725},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6626361608505249},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.655802845954895},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6103008389472961},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5767554640769958},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5557500720024109},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5185952186584473},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5095672607421875},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.437570720911026},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4218188226222992},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3801434636116028},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35835811495780945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.836242139339447},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6968324184417725},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6626361608505249},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.655802845954895},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6103008389472961},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5767554640769958},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5557500720024109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5185952186584473},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5095672607421875},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.437570720911026},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4218188226222992},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3801434636116028},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35835811495780945},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461614","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W73572011","https://openalex.org/W104184427","https://openalex.org/W567546468","https://openalex.org/W1523135049","https://openalex.org/W1592672653","https://openalex.org/W1904365287","https://openalex.org/W1956164794","https://openalex.org/W1970890968","https://openalex.org/W2038810952","https://openalex.org/W2079623482","https://openalex.org/W2092845679","https://openalex.org/W2120209245","https://openalex.org/W2127141656","https://openalex.org/W2129070077","https://openalex.org/W2137630452","https://openalex.org/W2402318445","https://openalex.org/W2515572005","https://openalex.org/W2545177271","https://openalex.org/W2963537349","https://openalex.org/W3202208228","https://openalex.org/W6604254268","https://openalex.org/W6640835780","https://openalex.org/W6660385150","https://openalex.org/W6677771871","https://openalex.org/W6679097437","https://openalex.org/W6680394064","https://openalex.org/W6713103005","https://openalex.org/W6802213812"],"related_works":["https://openalex.org/W2978673814","https://openalex.org/W2963920996","https://openalex.org/W1489125746","https://openalex.org/W4297665160","https://openalex.org/W1516378513","https://openalex.org/W1533416326","https://openalex.org/W2115353073","https://openalex.org/W2996122240","https://openalex.org/W2944384275","https://openalex.org/W4321603164"],"abstract_inverted_index":{"In":[0,74],"this":[1,34,75,94,107],"work,":[2,76],"we":[3,36,77,89,96],"focus":[4],"on":[5,9,62,93],"multilingual":[6,25,47],"systems":[7],"based":[8,123],"recurrent":[10],"neural":[11],"networks":[12],"(RNNs),":[13],"trained":[14],"using":[15,103],"the":[16,63,72,98,129,136,139],"Connectionist":[17],"Temporal":[18],"Classification":[19],"(CTC)":[20],"loss":[21],"function.":[22],"Using":[23],"a":[24,85],"set":[26],"of":[27,71,101,138],"acoustic":[28],"units":[29],"poses":[30],"difficulties.":[31],"To":[32],"address":[33],"issue,":[35],"proposed":[37],"Language":[38,49],"Feature":[39],"Vectors":[40],"(LFV":[41],"s)":[42],"to":[43,53,57,68],"train":[44],"language":[45],"adaptive":[46],"systems.":[48,124],"adaptation,":[50,55],"in":[51,109],"contrast":[52],"speaker":[54],"needs":[56],"be":[58,133],"applied":[59],"not":[60],"only":[61],"feature":[64],"level,":[65],"but":[66],"also":[67],"deeper":[69],"layers":[70,100],"network.":[73],"therefore":[78],"extended":[79],"our":[80],"previous":[81],"approach":[82,108],"by":[83,135],"introducing":[84],"novel":[86],"technique":[87],"which":[88],"call":[90],"\u201cmodulation\u201d.":[91],"Based":[92],"method,":[95],"modulated":[97],"hidden":[99],"RNNs":[102],"LFVs.":[104],"We":[105],"evaluated":[106],"both":[110],"full":[111],"and":[112,121],"low":[113],"resource":[114],"conditions,":[115],"as":[116,118],"well":[117],"for":[119],"grapheme":[120],"phone":[122],"Lower":[125],"error":[126],"rates":[127],"throughout":[128],"different":[130],"conditions":[131],"could":[132],"achieved":[134],"use":[137],"modulation.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
