{"id":"https://openalex.org/W2889785444","doi":"https://doi.org/10.1109/slt.2018.8639566","title":"Advancing Multi-Accented Lstm-CTC Speech Recognition Using a Domain Specific Student-Teacher Learning Paradigm","display_name":"Advancing Multi-Accented Lstm-CTC Speech Recognition Using a Domain Specific Student-Teacher Learning Paradigm","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2889785444","doi":"https://doi.org/10.1109/slt.2018.8639566","mag":"2889785444"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639566","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639566","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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/A5075220607","display_name":"Shahram Ghorbani","orcid":"https://orcid.org/0000-0002-8118-5515"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shahram Ghorbani","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas, Dallas, Richardson, TX 75080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas, Dallas, Richardson, TX 75080","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072597547","display_name":"Ahmet Bulut","orcid":"https://orcid.org/0000-0002-9435-287X"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmet E. Bulut","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas, Dallas, Richardson, TX 75080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas, Dallas, Richardson, TX 75080","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas, Dallas, Richardson, TX 75080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas, Dallas, Richardson, TX 75080","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1964,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90674703,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"29","last_page":"35"},"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":0.9977999925613403,"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":0.9976000189781189,"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":0.7725963592529297},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6378674507141113},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6087269186973572},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6016358137130737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5466639399528503},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.49020177125930786},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48248767852783203},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4430193305015564},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.413326621055603},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3649892807006836},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15146973729133606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7725963592529297},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6378674507141113},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6087269186973572},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6016358137130737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5466639399528503},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.49020177125930786},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48248767852783203},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4430193305015564},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.413326621055603},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3649892807006836},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15146973729133606},{"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/slt.2018.8639566","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639566","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8700000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1499864241","https://openalex.org/W1499999342","https://openalex.org/W1533416326","https://openalex.org/W1821462560","https://openalex.org/W2005708641","https://openalex.org/W2079735306","https://openalex.org/W2102113734","https://openalex.org/W2103962059","https://openalex.org/W2134797427","https://openalex.org/W2143612262","https://openalex.org/W2193413348","https://openalex.org/W2233435981","https://openalex.org/W2291513470","https://openalex.org/W2399104796","https://openalex.org/W2579851902","https://openalex.org/W2587080466","https://openalex.org/W2603679025","https://openalex.org/W2633884958","https://openalex.org/W2680270903","https://openalex.org/W2711861986","https://openalex.org/W2747909401","https://openalex.org/W2748545504","https://openalex.org/W2888884590","https://openalex.org/W2889488531","https://openalex.org/W2962893195","https://openalex.org/W2963920996","https://openalex.org/W2964107261","https://openalex.org/W6629052376","https://openalex.org/W6629930100","https://openalex.org/W6638523607","https://openalex.org/W6675365184","https://openalex.org/W6679909955","https://openalex.org/W6687566353","https://openalex.org/W6712831500","https://openalex.org/W6746405711","https://openalex.org/W6746497793"],"related_works":["https://openalex.org/W117063597","https://openalex.org/W4289544804","https://openalex.org/W3031252497","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W4398173524","https://openalex.org/W4290708361","https://openalex.org/W2129812225"],"abstract_inverted_index":{"Non-native":[0],"speech":[1,4],"causes":[2],"automatic":[3],"recognition":[5],"systems":[6],"to":[7,13,72,129,195,219,228,248],"degrade":[8],"in":[9,157,179,243],"performance.":[10],"Past":[11],"strategies":[12],"address":[14,139],"this":[15,32,140,203],"challenge":[16],"have":[17],"considered":[18],"model":[19,25,66,83,100,170,218],"adaptation,":[20],"accent":[21,144,214,224],"classification":[22,44],"with":[23,41,68],"a":[24,36,65,81,96,102,151,168,234],"selection,":[26],"alternate":[27],"pronunciation":[28],"lexicon,":[29],"etc.":[30],"In":[31],"study,":[33],"we":[34,142,166,207],"consider":[35],"recurrent":[37],"neural":[38],"network":[39],"(RNN)":[40],"connectionist":[42],"temporal":[43],"(CTC)":[45],"cost":[46,86],"function":[47],"trained":[48,67,99,118,162,198],"on":[49],"multi-accent":[50,70,153,205],"English":[51],"data":[52,71],"including":[53],"US":[54],"(Native),":[55],"Indian":[56],"and":[57,84,161],"Hispanic":[58],"accents.":[59],"We":[60,90],"exploit":[61],"dark":[62],"knowledge":[63,94,235],"from":[64,95],"the":[69,77,109,114,148,172,175,196,217,223,230,249],"train":[73,143,167],"student":[74,103,169],"models":[75,120,146],"under":[76,147,171],"guidance":[78,149],"of":[79,87,116,134,150,174,238],"both":[80],"teacher":[82,111,136,254],"CTC":[85,119,135,163],"target":[88],"transcription.":[89],"show":[91],"that":[92],"transferring":[93],"single":[97,152],"RNN-CTC":[98],"toward":[101],"model,":[104,184,206],"yields":[105],"better":[106],"performance":[107,246],"than":[108],"stand-alone":[110],"model.":[112],"Since":[113],"outputs":[115,227],"different":[117],"are":[121],"not":[122,127],"necessarily":[123],"aligned,":[124],"it":[125],"is":[126],"possible":[128],"simply":[130],"use":[131],"an":[132,180],"ensemble":[133],"models.":[137,164,255],"To":[138],"problem,":[141],"specific":[145,225],"teacher,":[154],"which":[155,185],"results":[156,242],"having":[158],"multiple":[159],"aligned":[160],"Furthermore,":[165],"supervision":[173],"accent-specific":[176],"teachers,":[177],"resulting":[178],"even":[181,244],"further":[182,210],"complementary":[183],"achieves":[186],"+20.1%":[187],"relative":[188],"Character":[189],"Error":[190],"Rate":[191],"(CER)":[192],"reduction":[193],"compared":[194,247],"baseline":[197],"without":[199],"any":[200],"teacher.":[201],"Having":[202],"effective":[204],"can":[208],"achieve":[209],"improvement":[211],"for":[212],"each":[213,220],"by":[215],"adapting":[216,231],"accent.":[221],"Using":[222],"model's":[226],"regularize":[229],"process":[232],"(i.e.,":[233],"distillation":[236],"version":[237],"Kullback-Leibler":[239],"(KL)":[240],"divergence)":[241],"superior":[245],"conventional":[250],"approach":[251],"using":[252],"general":[253]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}