{"id":"https://openalex.org/W3197144816","doi":"https://doi.org/10.1186/s13636-021-00222-7","title":"Pronunciation augmentation for Mandarin-English code-switching speech recognition","display_name":"Pronunciation augmentation for Mandarin-English code-switching speech recognition","publication_year":2021,"publication_date":"2021-08-30","ids":{"openalex":"https://openalex.org/W3197144816","doi":"https://doi.org/10.1186/s13636-021-00222-7","mag":"3197144816"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-021-00222-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00222-7","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00222-7","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00222-7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056415893","display_name":"Yanhua Long","orcid":"https://orcid.org/0000-0003-0924-408X"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanhua Long","raw_affiliation_strings":["SHNU-Unisound Joint Laboratory of Natural Human-Computer Interaction, Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"SHNU-Unisound Joint Laboratory of Natural Human-Computer Interaction, Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101917656","display_name":"Shuang Wei","orcid":"https://orcid.org/0000-0002-6250-6926"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Wei","raw_affiliation_strings":["SHNU-Unisound Joint Laboratory of Natural Human-Computer Interaction, Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"SHNU-Unisound Joint Laboratory of Natural Human-Computer Interaction, Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618320","display_name":"Jie Lian","orcid":"https://orcid.org/0000-0002-2005-2022"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Lian","raw_affiliation_strings":["SHNU-Unisound Joint Laboratory of Natural Human-Computer Interaction, Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"SHNU-Unisound Joint Laboratory of Natural Human-Computer Interaction, Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039983089","display_name":"Yijie Li","orcid":"https://orcid.org/0009-0004-3636-9624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yijie Li","raw_affiliation_strings":["Unisound AI Technology Co., Ltd., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co., Ltd., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056415893"],"corresponding_institution_ids":["https://openalex.org/I21945476"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":0.8399,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78949503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2021","issue":"1","first_page":null,"last_page":null},"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/T10860","display_name":"Speech and Audio Processing","score":0.9976999759674072,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8876140117645264},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.8729032874107361},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6948917508125305},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6941362619400024},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6759292483329773},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6215592622756958},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.580175518989563},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5500510931015015},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5311760902404785},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4859682321548462},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47525522112846375},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.4675181210041046},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.44271084666252136},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24240559339523315},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06557348370552063}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8876140117645264},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8729032874107361},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6948917508125305},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6941362619400024},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6759292483329773},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6215592622756958},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.580175518989563},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5500510931015015},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5311760902404785},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4859682321548462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47525522112846375},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4675181210041046},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.44271084666252136},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24240559339523315},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06557348370552063},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-021-00222-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00222-7","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00222-7","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:92d128eb038247faab479c14647cde6a","is_oa":true,"landing_page_url":"https://doaj.org/article/92d128eb038247faab479c14647cde6a","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2021, Iss 1, Pp 1-14 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-021-00222-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00222-7","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00222-7","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G514874842","display_name":null,"funder_award_id":"62071302","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6811802783","display_name":null,"funder_award_id":"6207130","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7376540038","display_name":null,"funder_award_id":"61701306","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8863666567","display_name":null,"funder_award_id":"and No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3197144816.pdf","grobid_xml":"https://content.openalex.org/works/W3197144816.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W197277712","https://openalex.org/W1524333225","https://openalex.org/W1952967124","https://openalex.org/W1972711991","https://openalex.org/W2000688218","https://openalex.org/W2031292349","https://openalex.org/W2056200968","https://openalex.org/W2080550848","https://openalex.org/W2084543186","https://openalex.org/W2090755665","https://openalex.org/W2094342469","https://openalex.org/W2103635804","https://openalex.org/W2130414229","https://openalex.org/W2132974827","https://openalex.org/W2153433699","https://openalex.org/W2154607443","https://openalex.org/W2160815625","https://openalex.org/W2161490380","https://openalex.org/W2170070437","https://openalex.org/W2184045248","https://openalex.org/W2407080277","https://openalex.org/W2407467516","https://openalex.org/W2514741789","https://openalex.org/W2592562038","https://openalex.org/W2735006420","https://openalex.org/W2742223267","https://openalex.org/W2747135936","https://openalex.org/W2791281350","https://openalex.org/W2798348125","https://openalex.org/W2811159785","https://openalex.org/W2892009249","https://openalex.org/W2896082894","https://openalex.org/W2896558859","https://openalex.org/W2899879954","https://openalex.org/W2926989360","https://openalex.org/W2936774411","https://openalex.org/W2937754410","https://openalex.org/W2938792232","https://openalex.org/W2939069254","https://openalex.org/W2939757332","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2963403868","https://openalex.org/W2963573574","https://openalex.org/W2964107261","https://openalex.org/W2964156075","https://openalex.org/W2964190464","https://openalex.org/W2972324550","https://openalex.org/W2972417954","https://openalex.org/W2972702443","https://openalex.org/W2973029565","https://openalex.org/W2978329087","https://openalex.org/W2996952407","https://openalex.org/W3029286132","https://openalex.org/W3116444474","https://openalex.org/W3137778678","https://openalex.org/W4247981272"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2366752344"],"abstract_inverted_index":{"Abstract":[0],"Code-switching":[1],"(CS)":[2],"refers":[3],"to":[4,21,27,88,107,111],"the":[5,28,34,39,44,54,64,69,113,134,142,146,157,167],"phenomenon":[6,37],"of":[7,38,72,119,133,141,169],"using":[8,75],"more":[9],"than":[10],"one":[11,32],"language":[12,41],"in":[13,31],"an":[14,98],"utterance,":[15,33],"and":[16,43,67,145,161],"it":[17],"presents":[18],"great":[19],"challenge":[20],"automatic":[22],"speech":[23,149,171],"recognition":[24,150],"(ASR)":[25],"due":[26],"code-switching":[29,170],"property":[30],"pronunciation":[35,65,76,117],"variation":[36,66],"embedding":[40,121],"words":[42],"heavy":[45],"training":[46],"data":[47],"sparse":[48,70],"problem.":[49],"This":[50],"paper":[51],"focuses":[52],"on":[53,95,127,139],"Mandarin-English":[55],"CS":[56,92,129],"ASR":[57,130],"task.":[58],"We":[59],"aim":[60],"at":[61],"dealing":[62],"with":[63],"alleviating":[68],"problem":[71],"code-switches":[73],"by":[74],"augmentation":[77],"methods.":[78],"An":[79],"English-to-Mandarin":[80],"mix-language":[81],"phone":[82,159],"mapping":[83,160],"approach":[84],"is":[85,104],"first":[86],"proposed":[87,106,135],"obtain":[89],"a":[90],"language-universal":[91],"lexicon.":[93],"Based":[94],"this":[96],"lexicon,":[97],"acoustic":[99],"data-driven":[100],"lexicon":[101],"learning":[102],"framework":[103],"further":[105],"learn":[108],"new":[109],"pronunciations":[110,163],"cover":[112],"accents,":[114],"mis-pronunciations,":[115],"or":[116],"variations":[118],"those":[120],"English":[122],"words.":[123],"Experiments":[124],"are":[125,137],"performed":[126],"real":[128],"tasks.":[131],"Effectiveness":[132],"methods":[136],"examined":[138],"all":[140],"conventional,":[143],"hybrid,":[144],"recent":[147],"end-to-end":[148],"systems.":[151],"Experimental":[152],"results":[153],"show":[154],"that":[155],"both":[156],"learned":[158],"augmented":[162],"can":[164],"significantly":[165],"improve":[166],"performance":[168],"recognition.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}