{"id":"https://openalex.org/W2920819083","doi":"https://doi.org/10.23919/apsipa.2018.8659508","title":"Map and Relabel: Towards Almost-Zero Resource Speech Recognition","display_name":"Map and Relabel: Towards Almost-Zero Resource Speech Recognition","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2920819083","doi":"https://doi.org/10.23919/apsipa.2018.8659508","mag":"2920819083"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659508","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5102001805","display_name":"Ying Shi","orcid":"https://orcid.org/0000-0001-8445-2300"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ying Shi","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056437232","display_name":"Zhiyuan Tang","orcid":"https://orcid.org/0000-0002-3786-7690"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Tang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056675605","display_name":"Lantian Lit","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lantian Lit","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021672160","display_name":"Zheling Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheling Zhang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391494","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6992-7950"},"institutions":[{"id":"https://openalex.org/I29955533","display_name":"Center for Information Technology","ror":"https://ror.org/03jh5a977","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I29955533"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology","institution_ids":["https://openalex.org/I29955533"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102001805"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.3258,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69760652,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"591","last_page":"595"},"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":0.9933000206947327,"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":0.9919000267982483,"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":0.8386752605438232},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6700042486190796},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6693561673164368},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6012737154960632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5121805667877197},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4698430895805359},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4694368839263916},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46878042817115784},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43994638323783875},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.4383578300476074},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.42024940252304077},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39552515745162964}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8386752605438232},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6700042486190796},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6693561673164368},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6012737154960632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5121805667877197},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4698430895805359},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4694368839263916},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46878042817115784},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43994638323783875},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.4383578300476074},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.42024940252304077},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39552515745162964},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659508","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7200000286102295,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1970890968","https://openalex.org/W1975550806","https://openalex.org/W1978660892","https://openalex.org/W1993660824","https://openalex.org/W1994606281","https://openalex.org/W2025198378","https://openalex.org/W2092286949","https://openalex.org/W2107553890","https://openalex.org/W2136504847","https://openalex.org/W2160815625","https://openalex.org/W2172130635","https://openalex.org/W2286443923","https://openalex.org/W2807869487","https://openalex.org/W2963522845","https://openalex.org/W4249319664","https://openalex.org/W6695606915"],"related_works":["https://openalex.org/W618248309","https://openalex.org/W2377336366","https://openalex.org/W1601203902","https://openalex.org/W2102464536","https://openalex.org/W2361332776","https://openalex.org/W4225671779","https://openalex.org/W1568097102","https://openalex.org/W4390419160","https://openalex.org/W2897407000","https://openalex.org/W4295705264"],"abstract_inverted_index":{"Modern":[0],"automatic":[1],"speech":[2,179],"recognition":[3],"(ASR)":[4],"systems":[5,119],"require":[6],"large":[7,175],"amounts":[8],"of":[9,27,43,65,79,93,177],"data":[10,38,64,184],"to":[11,52,168,188,234,250],"train":[12,117,189,215],"the":[13,18,28,31,41,77,151,156,202,245],"acoustic":[14],"model,":[15],"especially":[16],"with":[17,63,123],"state-of-the-art":[19,50],"deep":[20],"neural":[21],"network":[22],"(DNN)":[23],"architecture.":[24],"Unfortunately,":[25],"most":[26],"languages":[29,122],"in":[30,46,76,138,201],"world":[32],"have":[33],"very":[34],"limited":[35,152],"accumulating":[36],"for":[37,100,120,173,241],"resources,":[39],"limiting":[40],"application":[42],"ASR":[44,118,219,239],"technologies":[45],"these":[47],"languages.":[48,102],"The":[49],"approach":[51,114,131,160,209],"tackle":[53],"this":[54,104,163,207],"problem":[55],"is":[56,96,165,210,232,252],"transfer":[57,133,158],"learning,":[58],"by":[59,72,222],"which":[60,95],"DNNs":[61],"trained":[62],"a":[66,108,125,139,145,174,190,197,216,237],"rich-resource":[67],"language":[68,74,200],"can":[69,116,214],"be":[70],"reused":[71],"low-resource":[73],"systems,":[75],"form":[78],"either":[80],"feature":[81],"extractor":[82],"or":[83],"initial":[84],"model.":[85],"This":[86,130,226],"approach,":[87],"however,":[88],"still":[89,97],"requires":[90],"several":[91,255],"hours":[92],"speech,":[94],"not":[98],"affordable":[99],"many":[101],"In":[103],"study,":[105],"we":[106,248],"present":[107],"novel":[109],"Map":[110],"and":[111,135,244],"Relabel":[112],"(MaR)":[113],"that":[115,206,230],"new":[121],"only":[124,223,246],"few":[126],"hundred":[127,256],"labelled":[128],"utterances.":[129,225,257],"combines":[132],"learning":[134,137,159],"semi-supervised":[136],"boosting":[140],"manner:":[141],"it":[142,213,231],"firstly":[143],"trains":[144],"simple":[146],"monophone":[147],"DNN":[148],"based":[149],"on":[150,195],"training":[153],"data,":[154],"employing":[155],"popular":[157],"(Map":[161],"phase);":[162],"model":[164],"then":[166,186],"used":[167,187],"produce":[169],"pseudo":[170],"phone":[171],"labels":[172],"amount":[176],"untranscribed":[178],"(Relabel":[180],"phase).":[181],"These":[182],"pseudo-labelled":[183],"are":[185],"full-fledged":[191],"tri-phone":[192],"system.":[193],"Experiments":[194],"Uyghur,":[196],"major":[198],"minority":[199],"western":[203],"China,":[204],"demonstrates":[205],"MaR":[208],"rather":[211],"successful:":[212],"pretty":[217],"good":[218],"Uyghur":[220],"system":[221,240],"500":[224],"encouraging":[227],"results":[228],"indicate":[229],"possible":[233],"quickly":[235],"construct":[236],"reasonable":[238],"any":[242],"language,":[243],"effort":[247],"need":[249],"pay":[251],"just":[253],"labelling":[254]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}