{"id":"https://openalex.org/W2587080466","doi":"https://doi.org/10.1109/slt.2016.7846328","title":"Towards acoustic model unification across dialects","display_name":"Towards acoustic model unification across dialects","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2587080466","doi":"https://doi.org/10.1109/slt.2016.7846328","mag":"2587080466"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2016.7846328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Spoken Language Technology Workshop (SLT)","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/A5111926790","display_name":"Mohamed Elfeky","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohamed Elfeky","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007691719","display_name":"Meysam Bastani","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meysam Bastani","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077786635","display_name":"Xavier Velez","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xavier Velez","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103874391","display_name":"Pedro J. Moreno","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pedro Moreno","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064711844","display_name":"Austin Waters","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Austin Waters","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"624","last_page":"628"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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":0.9988999962806702,"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":0.7376128435134888},{"id":"https://openalex.org/keywords/unification","display_name":"Unification","score":0.7127102017402649},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6795773506164551},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5749719142913818},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5334717631340027},{"id":"https://openalex.org/keywords/unified-model","display_name":"Unified Model","score":0.5259628295898438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5245423913002014},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5097610354423523},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4996209144592285},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4911822974681854},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4830230176448822},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4601614475250244},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.43389949202537537},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3307316303253174},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17609873414039612},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.114938884973526},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11251994967460632}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7376128435134888},{"id":"https://openalex.org/C96146094","wikidata":"https://www.wikidata.org/wiki/Q609057","display_name":"Unification","level":2,"score":0.7127102017402649},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6795773506164551},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5749719142913818},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5334717631340027},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.5259628295898438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5245423913002014},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5097610354423523},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4996209144592285},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4911822974681854},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4830230176448822},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4601614475250244},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.43389949202537537},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3307316303253174},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17609873414039612},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.114938884973526},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11251994967460632},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2016.7846328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7900000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1545083717","https://openalex.org/W1600744878","https://openalex.org/W1731081199","https://openalex.org/W1821462560","https://openalex.org/W2017517591","https://openalex.org/W2064675550","https://openalex.org/W2094035326","https://openalex.org/W2114016253","https://openalex.org/W2127141656","https://openalex.org/W2137630452","https://openalex.org/W2155770957","https://openalex.org/W2158069733","https://openalex.org/W2160815625","https://openalex.org/W2291513470","https://openalex.org/W2293634267","https://openalex.org/W2294108103","https://openalex.org/W2346488894","https://openalex.org/W2508418541","https://openalex.org/W2893449927","https://openalex.org/W2913340405","https://openalex.org/W6635768407","https://openalex.org/W6637618735","https://openalex.org/W6638523607","https://openalex.org/W6696934422"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W2594897229","https://openalex.org/W4221142855","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W2523799048","https://openalex.org/W2155620340","https://openalex.org/W2244609359"],"abstract_inverted_index":{"Acoustic":[0],"model":[1,48,93,113],"performance":[2,138],"typically":[3],"decreases":[4],"when":[5],"evaluated":[6],"on":[7,25,40,117],"a":[8,26,45,52,79,90,100],"dialectal":[9,119],"variation":[10],"of":[11,28,70,139],"the":[12,111,137,140],"same":[13],"language":[14],"that":[15,49,94,105,114],"was":[16],"not":[17],"used":[18],"during":[19],"training.":[20],"Similarly,":[21],"models":[22,73,142],"simultaneously":[23],"trained":[24,116],"group":[27],"dialects":[29,98],"tend":[30],"to":[31,88,96,110],"underperform":[32],"dialect-specific":[33,71,141],"models.":[34],"In":[35,64,82],"this":[36,132],"paper,":[37],"we":[38,66,84],"report":[39],"our":[41],"efforts":[42],"towards":[43],"building":[44],"unified":[46,91],"acoustic":[47,72,92],"can":[50],"serve":[51],"multi-dialectal":[53],"language.":[54],"Two":[55],"techniques":[56,107],"are":[57,108],"presented:":[58],"Distillation":[59],"and":[60,74,127],"MultiTask":[61],"Learning":[62],"(MTL).":[63],"Distillation,":[65],"use":[67],"an":[68],"ensemble":[69],"distill":[75],"its":[76],"knowledge":[77],"in":[78],"single":[80],"model.":[81],"MTL,":[83],"utilize":[85],"multitask":[86],"learning":[87],"train":[89],"learns":[95],"distinguish":[97],"as":[99],"side":[101],"task.":[102],"We":[103],"show":[104],"both":[106],"superior":[109],"jointly-trained":[112],"is":[115],"all":[118],"data,":[120],"reducing":[121],"word":[122],"error":[123],"rates":[124],"by":[125,143],"4:2%":[126],"0:6%,":[128],"respectively.":[129],"While":[130],"achieving":[131],"improvement,":[133],"neither":[134],"technique":[135],"degrades":[136],"more":[144],"than":[145],"3:4%.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}