{"id":"https://openalex.org/W2938948885","doi":"https://doi.org/10.1109/icassp.2019.8683484","title":"Neural Codes to Factor Language in Multilingual Speech Recognition","display_name":"Neural Codes to Factor Language in Multilingual Speech Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938948885","doi":"https://doi.org/10.1109/icassp.2019.8683484","mag":"2938948885"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/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":false,"raw_author_name":"Markus Muller","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":null,"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 Stuker","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":null,"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":0.328,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.58271157,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"8638","last_page":"8642"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.8484295606613159},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.7556449174880981},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5568785071372986},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5464467406272888},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4992690086364746},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.49881958961486816},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.49560844898223877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49058976769447327},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48582884669303894},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.474774569272995},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.4659465551376343},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.44327160716056824},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.31448298692703247},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21298545598983765},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13430926203727722}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8484295606613159},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.7556449174880981},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5568785071372986},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5464467406272888},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4992690086364746},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.49881958961486816},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.49560844898223877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49058976769447327},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48582884669303894},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.474774569272995},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.4659465551376343},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.44327160716056824},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.31448298692703247},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21298545598983765},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13430926203727722},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W47568227","https://openalex.org/W73572011","https://openalex.org/W567546468","https://openalex.org/W1592672653","https://openalex.org/W2027030707","https://openalex.org/W2079623482","https://openalex.org/W2106440210","https://openalex.org/W2127141656","https://openalex.org/W2137630452","https://openalex.org/W2150769028","https://openalex.org/W2327501763","https://openalex.org/W2398141357","https://openalex.org/W2402318445","https://openalex.org/W2515572005","https://openalex.org/W2545177271","https://openalex.org/W2786835190","https://openalex.org/W2911291251","https://openalex.org/W2963226322","https://openalex.org/W2963336460","https://openalex.org/W2963649564","https://openalex.org/W3202208228","https://openalex.org/W6601939441","https://openalex.org/W6713103005","https://openalex.org/W6728910023","https://openalex.org/W6747492260"],"related_works":["https://openalex.org/W2372020181","https://openalex.org/W2156531654","https://openalex.org/W1581723585","https://openalex.org/W4378714697","https://openalex.org/W2294330161","https://openalex.org/W2253069048","https://openalex.org/W2804553224","https://openalex.org/W140709781","https://openalex.org/W3214340375","https://openalex.org/W1510159504"],"abstract_inverted_index":{"In":[0,14,169],"the":[1,19,24,31,40,54,64,68,94,161,172,175,180,183,187],"past,":[2],"we":[3,17,117,130],"adapted":[4],"neural":[5],"network":[6,98],"based":[7,104],"multilingual":[8,124],"acoustic":[9],"models":[10],"using":[11,137,152],"language":[12,21,25,35,71,75,91,95,113,140,157],"codes.":[13],"this":[15,121],"work,":[16],"study":[18],"extracted":[20],"codes":[22,32,72],"and":[23,77,85,143,164],"properties":[26,80],"they":[27],"encode:":[28],"We":[29,135],"use":[30],"to":[33,126],"generate":[34],"prototype":[36,48],"vectors,":[37],"which":[38,109],"represent":[39],"features":[41],"of":[42,100,111,156,174],"a":[43,89,106,153],"language.":[44],"Computing":[45],"distances":[46],"between":[47],"vectors":[49],"shows":[50],"that":[51,70,120,151],"languages":[52],"from":[53],"same":[55],"family":[56],"have":[57],"smaller":[58],"distances.":[59],"This":[60],"structure":[61],"found":[62],"within":[63],"feature":[65],"representation":[66,92],"supports":[67],"assumption":[69],"do":[73],"encode":[74],"information":[76],"not":[78],"other":[79],"like,":[81],"e.g.":[82],"channel":[83],"characteristics,":[84],"in":[86],"addition":[87],"providing":[88],"richer":[90],"than":[93],"identity":[96],"alone.The":[97],"architecture":[99],"our":[101],"system":[102,162,184],"is":[103],"on":[105],"factorized":[107],"model,":[108],"consists":[110],"multiple":[112],"dependent":[114,141,158],"subnets.":[115],"While":[116],"recently":[118],"demonstrated":[119],"approach":[122],"enables":[123],"setups":[125],"outperform":[127],"monolingual":[128,188],"ones,":[129],"here":[131],"propose":[132],"further":[133,178],"optimizations.":[134],"evaluated":[136],"a)":[138],"more":[139],"subnets":[142,159],"b)":[144],"wider":[145],"BiLSTM":[146],"layers.":[147],"Our":[148],"results":[149],"indicate":[150],"larger":[154],"number":[155],"increases":[160],"performance":[163],"renders":[165],"phonetic":[166],"pretraining":[167],"superfluous.":[168],"addition,":[170],"increasing":[171],"size":[173],"hidden":[176],"layers":[177],"improved":[179],"performance,":[181],"with":[182],"now":[185],"outperforming":[186],"baseline":[189],"by":[190],"6.3%":[191],"relative.":[192]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}