{"id":"https://openalex.org/W3008092184","doi":"https://doi.org/10.1109/asru46091.2019.9003926","title":"Zero-Shot Code-Switching ASR and TTS with Multilingual Machine Speech Chain","display_name":"Zero-Shot Code-Switching ASR and TTS with Multilingual Machine Speech Chain","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008092184","doi":"https://doi.org/10.1109/asru46091.2019.9003926","mag":"3008092184"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003926","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","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/A5112547671","display_name":"Sahoko Nakayama","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Sahoko Nakayama","raw_affiliation_strings":["RIKEN, Center for Advanced Intelligence Project AIP,Japan","RIKEN, Center for Advanced Intelligence Project AIP, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP,Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038296765","display_name":"Andros Tjandra","orcid":"https://orcid.org/0000-0003-1246-5908"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Andros Tjandra","raw_affiliation_strings":["Nara Institute of Science and Technology,Japan","Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["RIKEN, Center for Advanced Intelligence Project AIP,Japan","RIKEN, Center for Advanced Intelligence Project AIP, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP,Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["RIKEN, Center for Advanced Intelligence Project AIP,Japan","RIKEN, Center for Advanced Intelligence Project AIP, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP,Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP, Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5112547671"],"corresponding_institution_ids":["https://openalex.org/I4210126580"],"apc_list":null,"apc_paid":null,"fwci":0.5772,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77202152,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"2019","issue":null,"first_page":"964","last_page":"971"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9973999857902527,"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":0.9883000254631042,"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":0.7745907306671143},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6712239384651184},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.6634244918823242},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5835056304931641},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.48916319012641907},{"id":"https://openalex.org/keywords/chain","display_name":"Chain (unit)","score":0.4784400761127472},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4316529631614685},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35135865211486816},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19296550750732422},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11796018481254578},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08828231692314148}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7745907306671143},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6712239384651184},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.6634244918823242},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5835056304931641},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.48916319012641907},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.4784400761127472},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4316529631614685},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35135865211486816},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19296550750732422},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11796018481254578},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08828231692314148},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"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},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru46091.2019.9003926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003926","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"mag:3041477874","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002265072837252","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W27961112","https://openalex.org/W206967138","https://openalex.org/W1571920584","https://openalex.org/W1595936136","https://openalex.org/W1902237438","https://openalex.org/W1921523184","https://openalex.org/W2039387825","https://openalex.org/W2099531983","https://openalex.org/W2123162330","https://openalex.org/W2127863960","https://openalex.org/W2132474591","https://openalex.org/W2153433699","https://openalex.org/W2327501763","https://openalex.org/W2345986601","https://openalex.org/W2400103538","https://openalex.org/W2525997790","https://openalex.org/W2550821151","https://openalex.org/W2554000662","https://openalex.org/W2596142952","https://openalex.org/W2604184139","https://openalex.org/W2612434969","https://openalex.org/W2748238740","https://openalex.org/W2891616026","https://openalex.org/W2899073901","https://openalex.org/W2899771611","https://openalex.org/W2911876655","https://openalex.org/W2936842814","https://openalex.org/W2939757332","https://openalex.org/W2962699523","https://openalex.org/W2962826786","https://openalex.org/W2963581463","https://openalex.org/W2963609956","https://openalex.org/W2963796886","https://openalex.org/W2964156075","https://openalex.org/W3210141620","https://openalex.org/W4247981272","https://openalex.org/W6601146891","https://openalex.org/W6634090158","https://openalex.org/W6635509183","https://openalex.org/W6674798237","https://openalex.org/W6679101406","https://openalex.org/W6679792012","https://openalex.org/W6730320939"],"related_works":["https://openalex.org/W2771594921","https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W4389976243","https://openalex.org/W2432897346","https://openalex.org/W2181336723","https://openalex.org/W3158134258","https://openalex.org/W3138119129","https://openalex.org/W2773965352","https://openalex.org/W2940588741"],"abstract_inverted_index":{"Constructing":[0],"automatic":[1],"speech":[2,23,33,91],"recognition":[3],"(ASR)":[4],"and":[5,24,47,67,93,133],"text-to-speech":[6],"(TTS)":[7],"for":[8],"code-switching":[9,22,83,101,124,139],"in":[10],"a":[11,15,18],"supervised":[12],"fashion":[13],"poses":[14],"challenge":[16],"since":[17,58],"large":[19],"amount":[20],"of":[21,82,121],"the":[25,64,69,89,96,115,119,122,129],"corresponding":[26],"transcription":[27],"are":[28,105],"usually":[29],"unavailable.":[30],"The":[31,43],"machine":[32,90],"chain":[34,92],"mechanism":[35],"can":[36,98,134],"be":[37],"utilized":[38],"to":[39,49,62],"achieve":[40],"semi-supervised":[41],"learning.":[42],"framework":[44],"enables":[45],"ASR":[46],"TTS":[48],"assist":[50],"each":[51],"other":[52],"when":[53],"they":[54],"receive":[55],"unpaired":[56],"data":[57],"it":[59],"allows":[60],"them":[61],"infer":[63],"missing":[65],"pair":[66],"optimize":[68],"models":[70],"with":[71,100,127,137],"reconstruction":[72],"loss.":[73],"In":[74],"this":[75],"study,":[76],"we":[77],"handle":[78],"multiple":[79],"language":[80,86,102,125,140],"pairs":[81,103,126,141],"by":[84],"integrating":[85],"embeddings":[87],"into":[88],"investigate":[94],"whether":[95],"model":[97,130],"perform":[99,136],"that":[104,114],"never":[106],"explicitly":[107],"seen":[108],"during":[109],"training.":[110],"Experimental":[111],"results":[112],"reveal":[113],"proposed":[116],"approach":[117],"improves":[118],"performance":[120],"multilingual":[123],"which":[128],"was":[131],"trained":[132],"also":[135],"unknown":[138],"without":[142],"directly":[143],"learning":[144],"on":[145],"it.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}