{"id":"https://openalex.org/W3085006933","doi":"https://doi.org/10.1109/access.2020.3023783","title":"End-to-End Amdo-Tibetan Speech Recognition Based on Knowledge Transfer","display_name":"End-to-End Amdo-Tibetan Speech Recognition Based on Knowledge Transfer","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3085006933","doi":"https://doi.org/10.1109/access.2020.3023783","mag":"3085006933"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.3023783","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3023783","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09195519.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09195519.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103260592","display_name":"Xiaojun Zhu","orcid":"https://orcid.org/0000-0002-5555-8082"},"institutions":[{"id":"https://openalex.org/I20616075","display_name":"Qinghai Normal University","ror":"https://ror.org/03az1t892","country_code":"CN","type":"education","lineage":["https://openalex.org/I20616075"]},{"id":"https://openalex.org/I4210140336","display_name":"Lanzhou City University","ror":"https://ror.org/03cd4ja39","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210140336"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Zhu","raw_affiliation_strings":["MOE Key Laboratory of Tibetan Information Processing, Xining, China","School of Computer Science and Technology, Qinghai Normal University, Xining, China","School of Electronic and Information Engineering, Lanzhou City University, Lanzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5555-8082","affiliations":[{"raw_affiliation_string":"MOE Key Laboratory of Tibetan Information Processing, Xining, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Technology, Qinghai Normal University, Xining, China","institution_ids":["https://openalex.org/I20616075"]},{"raw_affiliation_string":"School of Electronic and Information Engineering, Lanzhou City University, Lanzhou, China","institution_ids":["https://openalex.org/I4210140336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003314925","display_name":"Heming Huang","orcid":"https://orcid.org/0000-0002-8204-1484"},"institutions":[{"id":"https://openalex.org/I20616075","display_name":"Qinghai Normal University","ror":"https://ror.org/03az1t892","country_code":"CN","type":"education","lineage":["https://openalex.org/I20616075"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heming Huang","raw_affiliation_strings":["MOE Key Laboratory of Tibetan Information Processing, Xining, China","School of Computer Science and Technology, Qinghai Normal University, Xining, China"],"raw_orcid":"https://orcid.org/0000-0002-8204-1484","affiliations":[{"raw_affiliation_string":"MOE Key Laboratory of Tibetan Information Processing, Xining, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Technology, Qinghai Normal University, Xining, China","institution_ids":["https://openalex.org/I20616075"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.9479,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81269125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"8","issue":null,"first_page":"170991","last_page":"171000"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.9983999729156494,"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":0.8362047672271729},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.720258355140686},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6301798820495605},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.562542200088501},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5258803367614746},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5168574452400208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48048582673072815},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.4551104009151459},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43912458419799805},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4368303716182709},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4309678375720978},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42832517623901367},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4215674102306366},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.398220419883728},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.358503520488739},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08770623803138733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8362047672271729},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.720258355140686},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6301798820495605},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.562542200088501},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5258803367614746},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5168574452400208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48048582673072815},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.4551104009151459},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43912458419799805},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4368303716182709},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4309678375720978},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42832517623901367},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4215674102306366},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.398220419883728},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.358503520488739},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08770623803138733},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.3023783","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3023783","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09195519.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a37876ff217f460cb1c1412ca812dd85","is_oa":true,"landing_page_url":"https://doaj.org/article/a37876ff217f460cb1c1412ca812dd85","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":"IEEE Access, Vol 8, Pp 170991-171000 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.3023783","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3023783","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09195519.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G31396423","display_name":"\u57fa\u4e8e\u6df1\u5ea6\u8fc1\u79fb\u5b66\u4e60\u7684\u5b89\u591a\u85cf\u8bed\u8bed\u97f3\u8bc6\u522b\u7814\u7a76","funder_award_id":"62066039","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7449532805","display_name":"\u5148\u9a8c\u4fe1\u606f\u4e0e\u56fe\u8bba\u76f8\u7ed3\u5408\u7684\u56fe\u50cf\u5206\u5272\u65b9\u6cd5\u53ca\u5176\u5e94\u7528\u7814\u7a76","funder_award_id":"61662062","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7724682460","display_name":null,"funder_award_id":"2016-ZJ-904","funder_id":"https://openalex.org/F4320335921","funder_display_name":"Natural Science Foundation of Qinghai"}],"funders":[{"id":"https://openalex.org/F4320310636","display_name":"University of Regina","ror":"https://ror.org/03dzc0485"},{"id":"https://openalex.org/F4320311590","display_name":"Fordham University","ror":"https://ror.org/03qnxaf80"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327066","display_name":"Qinghai Normal University","ror":"https://ror.org/03az1t892"},{"id":"https://openalex.org/F4320335921","display_name":"Natural Science Foundation of Qinghai","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3085006933.pdf","grobid_xml":"https://content.openalex.org/works/W3085006933.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1985258458","https://openalex.org/W2112739286","https://openalex.org/W2327501763","https://openalex.org/W2509065397","https://openalex.org/W2765691677","https://openalex.org/W2766219058","https://openalex.org/W2766974873","https://openalex.org/W2767446000","https://openalex.org/W2787110826","https://openalex.org/W2790326622","https://openalex.org/W2793012778","https://openalex.org/W2794209590","https://openalex.org/W2808939837","https://openalex.org/W2810776797","https://openalex.org/W2885706078","https://openalex.org/W2893243126","https://openalex.org/W2900298217","https://openalex.org/W2905678190","https://openalex.org/W2906459023","https://openalex.org/W2920377649","https://openalex.org/W2942544643","https://openalex.org/W2944113786","https://openalex.org/W2946075412","https://openalex.org/W2950754393","https://openalex.org/W2951444698","https://openalex.org/W2963086459","https://openalex.org/W2963096935","https://openalex.org/W2963292011","https://openalex.org/W2963403868","https://openalex.org/W2964058423","https://openalex.org/W2967468707","https://openalex.org/W2969521066","https://openalex.org/W2972592847","https://openalex.org/W2973481893","https://openalex.org/W2982784916","https://openalex.org/W2984865357","https://openalex.org/W2987573151","https://openalex.org/W2990384275","https://openalex.org/W2995025901","https://openalex.org/W3098357269","https://openalex.org/W3104896896","https://openalex.org/W3105021688","https://openalex.org/W4385245566","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2395910192","https://openalex.org/W2112752961","https://openalex.org/W2113687551","https://openalex.org/W107086600","https://openalex.org/W2126322296","https://openalex.org/W2401827384","https://openalex.org/W4294771049","https://openalex.org/W642007152","https://openalex.org/W2341426843","https://openalex.org/W2131711534"],"abstract_inverted_index":{"The":[0],"end-to-end":[1,86],"speech":[2,22,63,71,87,98,114,180,222],"recognition":[3,23,64,72,88,115,181],"technology":[4],"solves":[5],"the":[6,20,30,39,50,59,62,85,93,101,108,112,120,123,126,133,141,152,160,172,177,183,202,212,218],"problem":[7,161,203],"that":[8,47,211],"each":[9],"component":[10],"is":[11,74,137,156,169,189,198],"independent":[12],"and":[13,35,56,80,105,149,182,194],"models":[14],"cannot":[15],"be":[16],"jointly":[17],"optimized":[18],"in":[19],"traditional":[21],"model.":[24,65,116],"It":[25,90],"incorporates":[26],"such":[27],"components":[28],"as":[29],"acoustic":[31],"model,":[32,34],"language":[33,167],"decoding":[36],"unit":[37],"of":[38,53,61,110,122,147,162,179,204,220],"hybrid":[40],"model":[41,83,168,174,214],"into":[42],"a":[43],"single":[44],"neural":[45],"network,":[46],"can":[48,91,215],"avoid":[49],"inherent":[51],"defects":[52],"multiple":[54],"modules":[55],"greatly":[57,106],"reduces":[58,107],"complexity":[60],"In":[66],"this":[67],"research,":[68],"an":[69,165],"Amdo-Tibetan":[70,97,113,221],"system":[73],"constructed":[75],"based":[76],"on":[77],"Listen,":[78],"Attend":[79],"Spell":[81],"(LAS)":[82],"by":[84],"technology.":[89],"realize":[92],"direct":[94],"conversion":[95],"from":[96],"sequence":[99,104],"to":[100,139,158,175,200],"corresponding":[102],"character":[103],"difficulty":[109],"building":[111],"To":[117],"further":[118],"improve":[119,140],"performance":[121,219],"proposed":[124,213],"system,":[125],"following":[127],"improvements":[128],"have":[129],"been":[130],"made:":[131],"firstly,":[132],"Multi-Head":[134],"Attention":[135],"mechanism":[136],"introduced":[138],"alignment":[142],"accuracy":[143,178],"between":[144],"state":[145],"vectors":[146],"decoder":[148],"encoder;":[150],"secondly,":[151],"label":[153],"smoothing":[154],"technique":[155],"adopted":[157],"solve":[159],"over-fitting;":[163],"thirdly,":[164],"N-gram":[166],"combined":[170],"with":[171],"LAS":[173],"increase":[176],"maximum":[184],"mutual":[185],"information":[186],"(MMI)":[187],"criterion":[188],"employed":[190],"for":[191],"discriminative":[192],"training;":[193],"finally,":[195],"transfer":[196],"learning":[197],"utilized":[199],"overcome":[201],"insufficient":[205],"training":[206],"data.":[207],"Experimental":[208],"results":[209],"show":[210],"significantly":[216],"enhance":[217],"recognition.":[223]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}