{"id":"https://openalex.org/W2809695831","doi":"https://doi.org/10.21437/interspeech.2018-1241","title":"Neural Language Codes for Multilingual Acoustic Models","display_name":"Neural Language Codes for Multilingual Acoustic Models","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2809695831","doi":"https://doi.org/10.21437/interspeech.2018-1241","mag":"2809695831"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1241","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1807.01956","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106134095","display_name":"Markus M\u00fcller","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":true,"raw_author_name":"Markus M\u00fcller","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065183855","display_name":"Sebastian St\u00fcker","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 St\u00fcker","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"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":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5106134095"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":0.1692,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59263641,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2419","last_page":"2423"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.8330641984939575},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6138507127761841},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6016255617141724},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5816848278045654},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5406432151794434},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5101388096809387},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5003829002380371},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.46642547845840454},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4391598105430603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43721821904182434},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.24374791979789734},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11102595925331116}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8330641984939575},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6138507127761841},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6016255617141724},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5816848278045654},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5406432151794434},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5101388096809387},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5003829002380371},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.46642547845840454},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4391598105430603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43721821904182434},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.24374791979789734},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11102595925331116},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2018-1241","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1807.01956","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1807.01956","pdf_url":"https://arxiv.org/pdf/1807.01956","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"raw_type":"text"},{"id":"mag:2809695831","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1807.01956","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1807.01956","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1807.01956","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},{"id":"doi:10.5445/ir/1000087582","is_oa":true,"landing_page_url":"https://doi.org/10.5445/ir/1000087582","pdf_url":null,"source":{"id":"https://openalex.org/S7407052948","display_name":"KITopen","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1807.01956","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1807.01956","pdf_url":"https://arxiv.org/pdf/1807.01956","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2809695831.pdf"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W47568227","https://openalex.org/W73572011","https://openalex.org/W104184427","https://openalex.org/W567546468","https://openalex.org/W1523135049","https://openalex.org/W1592672653","https://openalex.org/W2027030707","https://openalex.org/W2079623482","https://openalex.org/W2092845679","https://openalex.org/W2095705004","https://openalex.org/W2112679344","https://openalex.org/W2127141656","https://openalex.org/W2129070077","https://openalex.org/W2137630452","https://openalex.org/W2150769028","https://openalex.org/W2398141357","https://openalex.org/W2402318445","https://openalex.org/W2515572005","https://openalex.org/W2745596852","https://openalex.org/W2786835190","https://openalex.org/W2951327905","https://openalex.org/W2963336460","https://openalex.org/W3202208228","https://openalex.org/W3216632493"],"related_works":["https://openalex.org/W2963649564","https://openalex.org/W2938948885","https://openalex.org/W2964309797","https://openalex.org/W2964138625","https://openalex.org/W2943941772","https://openalex.org/W2937754410","https://openalex.org/W2891616026","https://openalex.org/W2920970185","https://openalex.org/W1978660892","https://openalex.org/W2743818757","https://openalex.org/W2938309556","https://openalex.org/W2769639994","https://openalex.org/W3033831118","https://openalex.org/W3105242324","https://openalex.org/W2950961956","https://openalex.org/W3005915390","https://openalex.org/W2785994290","https://openalex.org/W3015325583","https://openalex.org/W2909792778","https://openalex.org/W2079508481"],"abstract_inverted_index":{"Multilingual":[0],"Speech":[1],"Recognition":[2],"is":[3,84],"one":[4,112],"of":[5,121],"the":[6,34,87,101,119,141],"most":[7],"costly":[8],"AI":[9],"problems,":[10],"because":[11],"each":[12,38],"language":[13,39,115,143,168],"(7,000+)":[14],"and":[15,40,61,150,166,172],"even":[16],"different":[17,75],"accents":[18],"require":[19,56],"their":[20],"own":[21,44],"acoustic":[22,126,163],"models":[23],"to":[24,65,96,110,140],"obtain":[25],"best":[26,176],"recognition":[27,134,177],"performance.":[28,178],"Even":[29],"though":[30],"they":[31,55],"all":[32],"use":[33,107],"same":[35],"phoneme":[36],"symbols,":[37],"accent":[41],"imposes":[42],"its":[43],"coloring":[45,144],"or":[46,103,147],"\"twang\".":[47],"Many":[48],"adaptive":[49],"approaches":[50],"have":[51,111],"been":[52],"proposed,":[53],"but":[54],"further":[57],"training,":[58],"additional":[59],"data":[60],"generally":[62],"are":[63],"inferior":[64],"monolingually":[66,154],"trained":[67,155],"models.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72],"propose":[73],"a":[74,79],"approach":[76],"that":[77,83,94,132],"uses":[78],"large":[80],"multilingual":[81,135],"model":[82,127,158],"\\emph{modulated}":[85],"by":[86,90,161],"codes":[88],"generated":[89],"an":[91],"ancillary":[92],"network":[93,113],"learns":[95],"code":[97,116,169],"useful":[98],"differences":[99],"between":[100],"\"twangs\"":[102],"human":[104],"language.":[105],"We":[106],"Meta-Pi":[108,136],"networks":[109,137],"(the":[114,125],"net)":[117],"gate":[118],"activity":[120],"neurons":[122],"in":[123],"another":[124],"nets).":[128],"Our":[129],"results":[130],"show":[131],"during":[133],"quickly":[138],"adapt":[139],"proper":[142],"without":[145],"retraining":[146],"new":[148],"data,":[149],"perform":[151],"better":[152],"than":[153],"networks.":[156],"The":[157],"was":[159],"evaluated":[160],"training":[162],"modeling":[164],"nets":[165,170],"modulating":[167],"jointly":[171],"optimize":[173],"them":[174],"for":[175]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}