{"id":"https://openalex.org/W2938374794","doi":"https://doi.org/10.1109/icassp.2019.8683705","title":"A Highly Adaptive Acoustic Model for Accurate Multi-dialect Speech Recognition","display_name":"A Highly Adaptive Acoustic Model for Accurate Multi-dialect Speech Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938374794","doi":"https://doi.org/10.1109/icassp.2019.8683705","mag":"2938374794"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2205.03027","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032371858","display_name":"Sanghyun Yoo","orcid":"https://orcid.org/0000-0002-8097-7975"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sanghyun Yoo","raw_affiliation_strings":["Samsung Advanced Institute of Technology, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109866178","display_name":"Inchul Song","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Inchul Song","raw_affiliation_strings":["Samsung Advanced Institute of Technology, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086198262","display_name":"Yoshua Bengio","orcid":"https://orcid.org/0000-0002-9322-3515"},"institutions":[{"id":"https://openalex.org/I4210155582","display_name":"Centre Universitaire de Mila","ror":"https://ror.org/05s3cw058","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210155582"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA","DZ"],"is_corresponding":false,"raw_author_name":"Yoshua Bengio","raw_affiliation_strings":["Mila, Université de Montréal, Canada","Mila, Universit\u00e9 de Montr\u00e9al, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila, Université de Montréal, Canada","institution_ids":["https://openalex.org/I4210155582"]},{"raw_affiliation_string":"Mila, Universit\u00e9 de Montr\u00e9al, Canada","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6652,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.94391171,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5716","last_page":"5720"},"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":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7844867706298828},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6697596311569214},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5822291374206543},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5783591270446777},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5074686408042908},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.46253564953804016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4535246789455414},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45254775881767273},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3520873785018921},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.30735743045806885},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10528120398521423}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7844867706298828},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6697596311569214},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5822291374206543},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5783591270446777},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5074686408042908},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.46253564953804016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4535246789455414},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45254775881767273},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3520873785018921},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30735743045806885},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10528120398521423},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8683705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2205.03027","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.03027","pdf_url":"https://arxiv.org/pdf/2205.03027","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2205.03027","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.03027","pdf_url":"https://arxiv.org/pdf/2205.03027","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1993409002","https://openalex.org/W2150769028","https://openalex.org/W2187089797","https://openalex.org/W2193413348","https://openalex.org/W2294108103","https://openalex.org/W2405866807","https://openalex.org/W2545656684","https://openalex.org/W2587080466","https://openalex.org/W2727849499","https://openalex.org/W2734498959","https://openalex.org/W2760103357","https://openalex.org/W2879390606","https://openalex.org/W2886247548","https://openalex.org/W2889494795","https://openalex.org/W2962893195","https://openalex.org/W2962949994","https://openalex.org/W2963596039","https://openalex.org/W2964099675","https://openalex.org/W2964121744","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6687566353","https://openalex.org/W6696757691","https://openalex.org/W6713969595","https://openalex.org/W6729110096","https://openalex.org/W6740674931","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2944691285","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W26527944","https://openalex.org/W2523799048","https://openalex.org/W2155620340"],"abstract_inverted_index":{"Despite":[0],"the":[1,39,135,140],"success":[2],"of":[3,41],"deep":[4],"learning":[5],"in":[6,25,63,101],"speech":[7,10,78,131],"recognition,":[8],"multi-dialect":[9,77],"recognition":[11,79],"remains":[12],"a":[13,49,70,81,102,114,153],"difficult":[14],"problem.":[15],"Although":[16],"dialect-specific":[17,34,163],"acoustic":[18,52,72],"models":[19],"are":[20,28],"known":[21],"to":[22,31,120,152,162],"perform":[23],"well":[24,57],"general,":[26],"they":[27],"not":[29],"easy":[30],"maintain":[32],"when":[33],"data":[35],"is":[36,46,87],"scarce":[37],"and":[38,95,157],"number":[40],"dialects":[42,60,109],"for":[43,58,75,106],"each":[44],"language":[45],"large.":[47],"Therefore,":[48],"single":[50,82,154],"unified":[51],"model":[53],"(AM)":[54],"that":[55,134],"generalizes":[56],"many":[59],"has":[61],"been":[62],"demand.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68],"propose":[69,113],"novel":[71],"modeling":[73],"technique":[74],"accurate":[76],"with":[80,122],"AM.":[83],"Our":[84],"proposed":[85,136],"AM":[86,105,137,156],"dynamically":[88],"adapted":[89],"based":[90],"on":[91,128],"both":[92],"dialect":[93],"information":[94],"its":[96],"internal":[97],"representation,":[98],"which":[99],"results":[100,127],"highly":[103],"adaptive":[104],"handling":[107],"multiple":[108],"simultaneously.":[110],"We":[111],"also":[112],"simple":[115],"but":[116],"effective":[117],"training":[118],"method":[119],"deal":[121],"unseen":[123],"dialects.":[124],"The":[125],"experimental":[126],"large":[129],"scale":[130],"datasets":[132],"show":[133],"outperforms":[138],"all":[139],"previous":[141],"ones,":[142],"reducing":[143],"word":[144],"error":[145],"rates":[146],"(WERs)":[147],"by":[148,158],"8.11%":[149],"relative":[150,160],"compared":[151,161],"all-dialects":[155],"7.31%":[159],"AMs.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2019-04-25T00:00:00"}