{"id":"https://openalex.org/W3010643167","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023203","title":"Knowledge Distillation from Multilingual and Monolingual Teachers for End-to-End Multilingual Speech Recognition","display_name":"Knowledge Distillation from Multilingual and Monolingual Teachers for End-to-End Multilingual Speech Recognition","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3010643167","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023203","mag":"3010643167"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5101990769","display_name":"Jingyi Xu","orcid":"https://orcid.org/0009-0006-8565-7221"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyi Xu","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology in China,Hefei,China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology in China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology in China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology in China, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101505189","display_name":"Junfeng Hou","orcid":"https://orcid.org/0000-0003-3635-5332"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfeng Hou","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology in China,Hefei,China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology in China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology in China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology in China, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108427099","display_name":"Yan Song","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Song","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology in China,Hefei,China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology in China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology in China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology in China, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101085190","display_name":"Wu Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Guo","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology in China,Hefei,China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology in China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology in China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology in China, Hefei, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lirong Dai","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology in China,Hefei,China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology in China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology in China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology in China, Hefei, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"844","last_page":"849"},"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":0.9990000128746033,"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":0.9958999752998352,"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":0.8199588060379028},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5130699872970581},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.479341596364975},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.45586350560188293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4379216432571411},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.4323662519454956},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42638272047042847},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4221239984035492},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4210435748100281},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3433387279510498}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8199588060379028},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5130699872970581},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.479341596364975},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.45586350560188293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4379216432571411},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4323662519454956},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42638272047042847},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4221239984035492},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4210435748100281},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3433387279510498},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W73572011","https://openalex.org/W1821462560","https://openalex.org/W1968147312","https://openalex.org/W2033436836","https://openalex.org/W2136933783","https://openalex.org/W2183341477","https://openalex.org/W2508418541","https://openalex.org/W2512865187","https://openalex.org/W2530876040","https://openalex.org/W2633884958","https://openalex.org/W2747909401","https://openalex.org/W2803023299","https://openalex.org/W2888930363","https://openalex.org/W2889030467","https://openalex.org/W2891616026","https://openalex.org/W2905933322","https://openalex.org/W2939111082","https://openalex.org/W2949975180","https://openalex.org/W2952288254","https://openalex.org/W2952650870","https://openalex.org/W2963292011","https://openalex.org/W2963864497","https://openalex.org/W2964309797","https://openalex.org/W6602987424","https://openalex.org/W6638523607","https://openalex.org/W6680549991","https://openalex.org/W6722866051","https://openalex.org/W6728811460","https://openalex.org/W6751751081"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2916997151","https://openalex.org/W2949174760"],"abstract_inverted_index":{"Attention-based":[0],"encoder-decoder":[1],"models":[2,81],"significantly":[3,209],"reduce":[4],"the":[5,34,47,52,55,70,74,117,126,167,170,196,204,207,212],"burden":[6],"of":[7,15,51,73,91,101,169,206],"developing":[8],"multilingual":[9,76,86,105,112,118,132,192,213],"speech":[10,193],"recognition":[11,71],"systems.":[12],"By":[13],"means":[14],"end-to-end":[16,75],"modeling":[17],"and":[18,28,49,85,104,128,152,188,200],"parameters":[19],"sharing,":[20],"a":[21,109,143,157],"single":[22,35],"model":[23,36,114,172],"can":[24],"be":[25],"efficiently":[26],"trained":[27],"deployed":[29],"for":[30,146],"all":[31],"languages.":[32],"Although":[33],"benefits":[37],"from":[38,65,83,135,149,155],"jointly":[39],"training":[40,161],"across":[41],"different":[42],"languages,":[43,93],"it":[44],"should":[45],"handle":[46],"variation":[48],"diversity":[50],"languages":[53],"at":[54],"same":[56,110],"time.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61,94],"exploit":[62],"knowledge":[63,90,123,137],"distillation":[64,138,201],"multiple":[66,96,198],"teachers":[67,97,100,199],"to":[68,107,130,165,211],"improve":[69],"accuracy":[72],"model.":[77],"Considering":[78],"that":[79,116],"teacher":[80,106],"learning":[82],"monolingual":[84,99],"data":[87,127],"contain":[88],"distinct":[89],"specific":[92],"introduce":[95],"including":[98],"each":[102],"language,":[103],"teach":[108],"sized":[111],"student":[113,119,171,208],"so":[115],"will":[120],"learn":[121],"various":[122],"embedded":[124],"in":[125,178],"intend":[129],"outperform":[131],"teacher.":[133,214],"Different":[134],"conventional":[136],"which":[139],"usually":[140],"relies":[141],"on":[142,183],"linear":[144],"interpolation":[145],"hard":[147,174],"loss":[148],"true":[150],"label":[151],"soft":[153,176],"losses":[154,177],"teachers,":[156],"new":[158],"random":[159,179],"augmented":[160],"strategy":[162,202],"is":[163],"proposed":[164,197],"switch":[166],"optimization":[168],"between":[173],"or":[175],"order.":[180],"Our":[181],"experiments":[182],"Wall":[184],"Street":[185],"Journal":[186],"(English)":[187],"AISHELL-1":[189],"(Chinese)":[190],"composed":[191],"dataset":[194],"show":[195],"boost":[203],"performance":[205],"relative":[210]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}