{"id":"https://openalex.org/W4206191520","doi":"https://doi.org/10.1186/s13636-021-00233-4","title":"Improving low-resource Tibetan end-to-end ASR by multilingual and multilevel unit modeling","display_name":"Improving low-resource Tibetan end-to-end ASR by multilingual and multilevel unit modeling","publication_year":2022,"publication_date":"2022-01-12","ids":{"openalex":"https://openalex.org/W4206191520","doi":"https://doi.org/10.1186/s13636-021-00233-4"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-021-00233-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00233-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-021-00233-4","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/counter/pdf/10.1186/s13636-021-00233-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066338559","display_name":"Siqing Qin","orcid":"https://orcid.org/0009-0002-0786-4859"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siqing Qin","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050763764","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-4005-5036"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Sheng Li","raw_affiliation_strings":["National Institute of Information and Communications Technology (NICT), Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017251198","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Ishikawa, Japan","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041292431","display_name":"Lixin Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lixin Pan","raw_affiliation_strings":["Huiyan Technology(Tianjin) Co., Ltd., Tianjin, 300384, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huiyan Technology(Tianjin) Co., Ltd., Tianjin, 300384, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5053726259"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":2.9131,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.91829076,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"2022","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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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":0.9950000047683716,"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":0.7717561721801758},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5760806798934937},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5318564772605896},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5301552414894104},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.461703360080719},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44307276606559753},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.43741628527641296},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.43593600392341614},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40471309423446655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35342949628829956},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16384539008140564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7717561721801758},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5760806798934937},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5318564772605896},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5301552414894104},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.461703360080719},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44307276606559753},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.43741628527641296},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.43593600392341614},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40471309423446655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35342949628829956},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16384539008140564},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s13636-021-00233-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00233-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-021-00233-4","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:6dd8a3750e2547d9b60e5746b3f116d5","is_oa":true,"landing_page_url":"https://doaj.org/article/6dd8a3750e2547d9b60e5746b3f116d5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"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 2022, Iss 1, Pp 1-10 (2022)","raw_type":"article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50728055","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100930629","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"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":"Journal Article"}],"best_oa_location":{"id":"doi:10.1186/s13636-021-00233-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00233-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-021-00233-4","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":[{"id":"https://metadata.un.org/sdg/4","score":0.41999998688697815,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2134500649","display_name":null,"funder_award_id":"2018YFB1305200","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5633359880","display_name":null,"funder_award_id":"61771333","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6902439365","display_name":null,"funder_award_id":"18ZXZNGX00330","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4206191520.pdf","grobid_xml":"https://content.openalex.org/works/W4206191520.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1995562189","https://openalex.org/W2005708641","https://openalex.org/W2091432990","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2293634267","https://openalex.org/W2327501763","https://openalex.org/W2514741789","https://openalex.org/W2573846420","https://openalex.org/W2613532868","https://openalex.org/W2627092829","https://openalex.org/W2766219058","https://openalex.org/W2889282842","https://openalex.org/W2890197052","https://openalex.org/W2892009249","https://openalex.org/W2894835365","https://openalex.org/W2895468225","https://openalex.org/W2962778134","https://openalex.org/W2962780374","https://openalex.org/W2963088995","https://openalex.org/W2963211739","https://openalex.org/W2963240019","https://openalex.org/W2963242190","https://openalex.org/W2963292011","https://openalex.org/W2964107261","https://openalex.org/W3012217511","https://openalex.org/W3016057683","https://openalex.org/W4252331534","https://openalex.org/W6600277285"],"related_works":["https://openalex.org/W2153098279","https://openalex.org/W2150890698","https://openalex.org/W2061937230","https://openalex.org/W2401394187","https://openalex.org/W4245698648","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W1566315437"],"abstract_inverted_index":{"Abstract":[0],"Conventional":[1],"automatic":[2],"speech":[3,10,73,102,113],"recognition":[4,11,74,103,114],"(ASR)":[5],"and":[6,41,47,66,82,179,218],"emerging":[7],"end-to-end":[8],"(E2E)":[9],"have":[12],"achieved":[13],"promising":[14],"results":[15],"after":[16],"being":[17],"provided":[18],"with":[19,141,175],"sufficient":[20],"resources.":[21],"However,":[22],"for":[23,62,137,185],"low-resource":[24,107,215],"language,":[25],"the":[26,36,55,59,88,101,106,117,122,138,147,152,159,186,193,196,204,214,236,242,248,251],"current":[27],"ASR":[28,56,135,148,161,169,199,207],"is":[29,35,51,98,183],"still":[30],"challenging.":[31],"The":[32,93],"Lhasa":[33,60,108,139,216,249],"dialect":[34,40,61,109,140,217],"most":[37],"widespread":[38],"Tibetan":[39,72,160],"has":[42],"a":[43,132,166,220],"wealth":[44],"of":[45,90,95,105,155,195,203,247],"speakers":[46],"transcriptions.":[48],"Hence,":[49],"it":[50],"meaningful":[52],"to":[53,58,99,145,150,231,241],"apply":[54],"technique":[57],"historical":[63],"heritage":[64],"protection":[65],"cultural":[67],"exchange.":[68],"Previous":[69],"work":[70],"on":[71,76,116,121,158],"focused":[75],"selecting":[77],"phone-level":[78],"acoustic":[79],"modeling":[80],"units":[81],"incorporating":[83],"tonal":[84],"information":[85],"but":[86],"underestimated":[87],"influence":[89],"limited":[91],"data.":[92],"purpose":[94],"this":[96],"paper":[97],"improve":[100],"performance":[104,194,223,253],"by":[110,171,255],"adopting":[111],"multilingual":[112,167,244],"technology":[115],"E2E":[118,134,168,205,239,245],"structure":[119],"based":[120],"transfer":[123,127],"learning":[124],"framework.":[125],"Using":[126],"learning,":[128],"we":[129],"first":[130,187],"establish":[131],"monolingual":[133,238],"system":[136,170,200],"different":[142,176],"source":[143,156,177],"languages":[144,157,178],"initialize":[146],"model":[149,240,246],"compare":[151],"positive":[153],"effects":[154],"model.":[162],"We":[163],"further":[164],"propose":[165],"utilizing":[172],"initialization":[173],"strategies":[174],"multilevel":[180],"units,":[181],"which":[182],"proposed":[184,197,210],"time.":[188],"Our":[189,209],"experiments":[190],"show":[191],"that":[192,202],"method-based":[198],"exceeds":[201],"baseline":[206],"system.":[208],"method":[211],"effectively":[212],"models":[213],"achieves":[219],"relative":[221],"14.2%":[222],"improvement":[224],"in":[225,257],"character":[226],"error":[227],"rate":[228],"(CER)":[229],"compared":[230],"DNN-HMM":[232],"systems.":[233],"Moreover,":[234],"from":[235],"best":[237,243],"dialect,":[250],"system\u2019s":[252],"increased":[254],"8.4%":[256],"CER.":[258]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}