{"id":"https://openalex.org/W2891616026","doi":"https://doi.org/10.1109/icassp.2018.8462180","title":"An End-to-End Language-Tracking Speech Recognizer for Mixed-Language Speech","display_name":"An End-to-End Language-Tracking Speech Recognizer for Mixed-Language Speech","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891616026","doi":"https://doi.org/10.1109/icassp.2018.8462180","mag":"2891616026"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462180","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/A5110334536","display_name":"Hiroshi Seki","orcid":"https://orcid.org/0000-0002-1769-2627"},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Seki","raw_affiliation_strings":["Toyohashi University of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyohashi University of Technology, Japan","institution_ids":["https://openalex.org/I136259955"]}]},{"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/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":"Shinji Watanabe","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"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 Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"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":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"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":"John R. Hershey","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4919","last_page":"4923"},"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":0.9987999796867371,"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":0.9987999796867371,"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":0.8752189874649048},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.8170046806335449},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6579514741897583},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6312669515609741},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5947378873825073},{"id":"https://openalex.org/keywords/cache-language-model","display_name":"Cache language model","score":0.5314390063285828},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5209997296333313},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.4745146632194519},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.47027379274368286},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4608359932899475},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45008155703544617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43483155965805054},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4232724905014038},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.32282009720802307},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3090365529060364},{"id":"https://openalex.org/keywords/universal-networking-language","display_name":"Universal Networking Language","score":0.2690950632095337},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1526072919368744},{"id":"https://openalex.org/keywords/comprehension-approach","display_name":"Comprehension approach","score":0.06663963198661804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8752189874649048},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8170046806335449},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6579514741897583},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6312669515609741},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5947378873825073},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.5314390063285828},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5209997296333313},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.4745146632194519},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.47027379274368286},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4608359932899475},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45008155703544617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43483155965805054},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4232724905014038},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.32282009720802307},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3090365529060364},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.2690950632095337},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1526072919368744},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.06663963198661804},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462180","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":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W1526236009","https://openalex.org/W1970890968","https://openalex.org/W1982774639","https://openalex.org/W2085628288","https://openalex.org/W2091746061","https://openalex.org/W2096140469","https://openalex.org/W2154304575","https://openalex.org/W2193413348","https://openalex.org/W2296073425","https://openalex.org/W2512355221","https://openalex.org/W2545177271","https://openalex.org/W2577366047","https://openalex.org/W2627092829","https://openalex.org/W2786835190","https://openalex.org/W6601563604","https://openalex.org/W6683008568","https://openalex.org/W6687566353","https://openalex.org/W6725219515","https://openalex.org/W6728910023","https://openalex.org/W6732447497"],"related_works":["https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2036933852","https://openalex.org/W2152945827","https://openalex.org/W2059588204","https://openalex.org/W3129739276","https://openalex.org/W3213549959","https://openalex.org/W2015513221","https://openalex.org/W2183673572","https://openalex.org/W301864623"],"abstract_inverted_index":{"End-to-end":[0],"automatic":[1],"speech":[2,93,127],"recognition":[3],"(ASR)":[4],"can":[5,58],"significantly":[6],"reduce":[7],"the":[8,19,72,88,109,133],"burden":[9],"of":[10,108,122],"developing":[11],"ASR":[12,38],"systems":[13],"for":[14,21],"new":[15],"languages,":[16,61],"by":[17],"eliminating":[18],"need":[20],"linguistic":[22],"information":[23],"such":[24,94],"as":[25,95],"pronunciation":[26],"dictionaries.":[27],"This":[28],"also":[29],"creates":[30],"an":[31,84,112],"opportunity":[32],"to":[33,77,90,104],"build":[34],"a":[35,41,52,116,123],"monolithic":[36,53],"multilingual":[37],"system":[39],"with":[40,67,153],"language-independent":[42],"neural":[43,54],"network":[44,55],"architecture.":[45],"In":[46,97],"our":[47,102,141],"previous":[48,142],"work,":[49],"we":[50,100],"proposed":[51],"architecture":[56],"that":[57,119,132,149],"recognize":[59,91],"multiple":[60],"and":[62,114,140],"showed":[63],"its":[64],"effectiveness":[65],"compared":[66],"conventional":[68],"language-dependent":[69,138],"models.":[70],"However,":[71],"model":[73,103,135,143],"is":[74],"not":[75],"guaranteed":[76],"properly":[78],"handle":[79],"switches":[80],"in":[81],"language":[82,110,154],"within":[83,111],"utterance,":[85,113],"thus":[86],"lacking":[87],"flexibility":[89],"mixed-language":[92,126],"code-switching.":[96],"this":[98],"paper,":[99],"extend":[101],"enable":[105],"dynamic":[106],"tracking":[107],"propose":[115],"training":[117],"procedure":[118],"takes":[120],"advantage":[121],"newly":[124],"created":[125],"corpus.":[128],"Experimental":[129],"results":[130],"show":[131],"extended":[134],"outperforms":[136],"both":[137],"models":[139],"without":[144],"suffering":[145],"from":[146],"performance":[147],"degradation":[148],"could":[150],"be":[151],"associated":[152],"switching.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}