{"id":"https://openalex.org/W2773389940","doi":"https://doi.org/10.1109/taslp.2017.2782360","title":"Multitask Learning for Phone Recognition of Underresourced Languages Using Mismatched Transcription","display_name":"Multitask Learning for Phone Recognition of Underresourced Languages Using Mismatched Transcription","publication_year":2017,"publication_date":"2017-12-11","ids":{"openalex":"https://openalex.org/W2773389940","doi":"https://doi.org/10.1109/taslp.2017.2782360","mag":"2773389940"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2782360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2782360","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5051897589","display_name":"Van Hai","orcid":"https://orcid.org/0000-0002-9554-5171"},"institutions":[{"id":"https://openalex.org/I182526193","display_name":"Thuyloi University","ror":"https://ror.org/04afshy24","country_code":"VN","type":"education","lineage":["https://openalex.org/I182526193"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Van Hai Do","raw_affiliation_strings":["Thuyloi University, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"Thuyloi University, Hanoi, Vietnam","institution_ids":["https://openalex.org/I182526193"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014190404","display_name":"Nancy F. Chen","orcid":"https://orcid.org/0000-0003-0872-5877"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nancy F. Chen","raw_affiliation_strings":["Institute for Infocomm Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026225097","display_name":"Boon Pang Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Boon Pang Lim","raw_affiliation_strings":["Institute for Infocomm Research, Singapore","NovuMind Inc., Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"NovuMind Inc., Santa Clara, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark A. Hasegawa-Johnson","raw_affiliation_strings":["University of Illinois at Urbana\u2013Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana\u2013Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051897589"],"corresponding_institution_ids":["https://openalex.org/I182526193"],"apc_list":null,"apc_paid":null,"fwci":2.3403,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.91399901,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"26","issue":"3","first_page":"501","last_page":"514"},"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":0.9998000264167786,"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":0.9994000196456909,"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":0.7480422258377075},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6577125787734985},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6491315364837646},{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"Phonetic transcription","score":0.5355871319770813},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5296257138252258},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.513195812702179},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5105620622634888},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43982112407684326},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18317973613739014}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480422258377075},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6577125787734985},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6491315364837646},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.5355871319770813},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5296257138252258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.513195812702179},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5105620622634888},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43982112407684326},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18317973613739014},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2017.2782360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2782360","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8500000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W7869021","https://openalex.org/W51373460","https://openalex.org/W124530132","https://openalex.org/W1436754857","https://openalex.org/W1524333225","https://openalex.org/W1582482241","https://openalex.org/W1967684049","https://openalex.org/W1970890968","https://openalex.org/W1980850109","https://openalex.org/W2012897754","https://openalex.org/W2023952145","https://openalex.org/W2025198378","https://openalex.org/W2036043322","https://openalex.org/W2038810952","https://openalex.org/W2049633694","https://openalex.org/W2079508481","https://openalex.org/W2087395764","https://openalex.org/W2094035326","https://openalex.org/W2106440210","https://openalex.org/W2119207063","https://openalex.org/W2123798005","https://openalex.org/W2125007694","https://openalex.org/W2131042651","https://openalex.org/W2133013156","https://openalex.org/W2133267619","https://openalex.org/W2136504847","https://openalex.org/W2141994339","https://openalex.org/W2143104527","https://openalex.org/W2146168991","https://openalex.org/W2147276082","https://openalex.org/W2147768505","https://openalex.org/W2165698076","https://openalex.org/W2290788502","https://openalex.org/W2346255448","https://openalex.org/W2401728495","https://openalex.org/W2403821174","https://openalex.org/W2404172366","https://openalex.org/W2404291917","https://openalex.org/W2406324447","https://openalex.org/W2406536007","https://openalex.org/W2507826679","https://openalex.org/W2508214553","https://openalex.org/W2513516901","https://openalex.org/W2524233457","https://openalex.org/W2545319977","https://openalex.org/W2547138517","https://openalex.org/W2572178803","https://openalex.org/W2603169490","https://openalex.org/W2745880412","https://openalex.org/W2963242190","https://openalex.org/W2993330478","https://openalex.org/W4251448448","https://openalex.org/W4285719527","https://openalex.org/W6600329959","https://openalex.org/W6602136846","https://openalex.org/W6605052996","https://openalex.org/W6628467411","https://openalex.org/W6631362777","https://openalex.org/W6679564466","https://openalex.org/W6680140577","https://openalex.org/W6713625570","https://openalex.org/W6713685906","https://openalex.org/W6727135808","https://openalex.org/W6728833719","https://openalex.org/W6731810891","https://openalex.org/W6744786301"],"related_works":["https://openalex.org/W2621258238","https://openalex.org/W2136763963","https://openalex.org/W2132470403","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W3184123547","https://openalex.org/W2745284343","https://openalex.org/W2160030256","https://openalex.org/W2028097510"],"abstract_inverted_index":{"It":[0],"is":[1,19,45,108,131],"challenging":[2],"to":[3,22,46,78,101,133,213],"obtain":[4],"large":[5,156],"amounts":[6],"of":[7,25,28,37,50,67,75,96,113,140,144,154,158,222,247],"native":[8,76],"(matched)":[9],"labels":[10],"for":[11],"speech":[12,85,245],"audio":[13],"in":[14,32,86,124,218],"underresourced":[15,65,251],"languages.":[16],"This":[17,116],"challenge":[18],"often":[20],"due":[21],"a":[23,35,102,120,141,155,188],"lack":[24,36],"literate":[26],"speakers":[27],"the":[29,48,64,70,111,169,209,223,231],"language,":[30],"or":[31],"extreme":[33],"cases,":[34],"universally":[38],"acknowledged":[39],"orthography":[40],"as":[41,83,238,240],"well.":[42],"One":[43],"solution":[44],"increase":[47],"amount":[49],"labeled":[51],"data":[52],"by":[53,110],"using":[54,196],"mismatched":[55,97,159,162,210],"transcription,":[56],"which":[57,125],"employs":[58],"transcribers":[59],"who":[60],"do":[61],"not":[62],"speak":[63],"language":[66,72,90,252],"interest":[68],"called":[69],"target":[71,92],"(in":[73],"place":[74],"speakers),":[77],"transcribe":[79],"what":[80],"they":[81],"hear":[82],"nonsense":[84],"their":[87],"own":[88],"annotation":[89],"(\u2260":[91],"language).":[93],"Previous":[94],"uses":[95],"transcription":[98,104,146,160],"converted":[99],"it":[100],"probabilistic":[103],"(PT),":[105],"but":[106],"PT":[107,197],"limited":[109],"errors":[112],"nonnative":[114],"perception.":[115],"paper":[117],"proposes,":[118],"instead,":[119],"multitask":[121,170,224],"learning":[122,171,185],"framework":[123,172],"one":[126],"deep":[127],"neural":[128],"network":[129],"(DNN)":[130],"trained":[132,207],"optimize":[134],"two":[135],"separate":[136],"tasks:":[137],"acoustic":[138,152],"modeling":[139,153],"small":[142],"number":[143,157],"matched":[145,148],"with":[147,161,253],"target-language":[149],"graphemes;":[150],"and":[151,183,203,234],"annotation-language":[163],"graphemes.":[164],"We":[165],"find":[166],"that:":[167],"first,":[168],"gives":[173],"significant":[174],"improvement":[175],"over":[176],"monolingual,":[177],"semisupervised":[178],"learning,":[179],"multilingual":[180],"DNN":[181],"training,":[182],"transfer":[184],"baselines;":[186],"second,":[187],"Gaussian":[189],"Mixture":[190],"Model-Hidden-Markov":[191],"Model":[192],"(GMM-HMM)":[193],"model":[194],"adapted":[195],"improves":[198],"alignments,":[199,216],"thereby":[200],"improving":[201],"training;":[202],"third,":[204],"bottleneck":[205],"features":[206],"on":[208,230,241],"transcriptions":[211],"lead":[212],"even":[214],"better":[215],"resulting":[217],"further":[219],"performance":[220],"gains":[221],"DNN.":[225],"Our":[226],"experiments":[227],"are":[228],"conducted":[229],"IARPA":[232],"Georgian":[233],"Vietnamese":[235],"BABEL":[236],"corpora":[237],"well":[239],"our":[242],"newly":[243],"collected":[244],"corpus":[246],"Singapore":[248],"Hokkien,":[249],"an":[250],"no":[254],"standard":[255],"written":[256],"form.":[257]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}