{"id":"https://openalex.org/W2964099675","doi":"https://doi.org/10.1109/icassp.2018.8462557","title":"Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition","display_name":"Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2964099675","doi":"https://doi.org/10.1109/icassp.2018.8462557","mag":"2964099675"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","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/A5059726557","display_name":"Xuesong Yang","orcid":"https://orcid.org/0000-0001-8625-5044"},"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":true,"raw_author_name":"Xuesong Yang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015927589","display_name":"Kartik Audhkhasi","orcid":"https://orcid.org/0000-0002-2340-1144"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kartik Audhkhasi","raw_affiliation_strings":["IBM T. J. Watson Research Center, NY"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, NY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102902866","display_name":"Andrew Rosenberg","orcid":"https://orcid.org/0000-0003-1780-4390"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Rosenberg","raw_affiliation_strings":["IBM T. J. Watson Research Center, NY"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, NY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["IBM T. J. Watson Research Center, NY"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, NY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM T. J. Watson Research Center, NY"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, NY","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 Hasegawa-Johnson","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5059726557"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":6.0769,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.97066181,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"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/T10028","display_name":"Topic Modeling","score":0.996999979019165,"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":0.7797719240188599},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7467947006225586},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.626011848449707},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.601756751537323},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5695162415504456},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5574129223823547},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5388479232788086},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5175803899765015},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5092564821243286},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4501153230667114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4406622350215912},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2695384621620178},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08421987295150757}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7797719240188599},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7467947006225586},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.626011848449707},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.601756751537323},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5695162415504456},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5574129223823547},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5388479232788086},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5175803899765015},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5092564821243286},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4501153230667114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4406622350215912},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2695384621620178},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08421987295150757},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W5524598","https://openalex.org/W1489125746","https://openalex.org/W1522301498","https://openalex.org/W1586532344","https://openalex.org/W1922655562","https://openalex.org/W1942035323","https://openalex.org/W2101066392","https://openalex.org/W2102113734","https://openalex.org/W2113457868","https://openalex.org/W2120354757","https://openalex.org/W2155117693","https://openalex.org/W2193413348","https://openalex.org/W2238976804","https://openalex.org/W2293858598","https://openalex.org/W2294108103","https://openalex.org/W2327501763","https://openalex.org/W2346488894","https://openalex.org/W2405866807","https://openalex.org/W2533523411","https://openalex.org/W2587080466","https://openalex.org/W2597757402","https://openalex.org/W2603679025","https://openalex.org/W2893449927","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963266252","https://openalex.org/W4212793782","https://openalex.org/W4250135370","https://openalex.org/W4254365061","https://openalex.org/W6600211438","https://openalex.org/W6629052376","https://openalex.org/W6640708543","https://openalex.org/W6675365184","https://openalex.org/W6682658900","https://openalex.org/W6687566353","https://openalex.org/W6696757691","https://openalex.org/W6713969595","https://openalex.org/W6831217225"],"related_works":["https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W3133352777","https://openalex.org/W151018310","https://openalex.org/W2784059283","https://openalex.org/W4319779560","https://openalex.org/W2008737763","https://openalex.org/W4385611764","https://openalex.org/W2519224033"],"abstract_inverted_index":{"The":[0,28],"performance":[1],"of":[2,25],"automatic":[3],"speech":[4],"recognition":[5],"systems":[6],"degrades":[7],"with":[8,33,128],"increasing":[9],"mismatch":[10],"between":[11],"the":[12,80,97],"training":[13,43],"and":[14,44,73,86,116],"testing":[15],"scenarios.":[16],"Differences":[17],"in":[18,49,109],"speaker":[19],"accents":[20,35,41],"are":[21],"a":[22,46,74,105],"significant":[23],"source":[24],"such":[26],"mismatch.":[27],"traditional":[29],"approach":[30],"to":[31,55],"deal":[32],"multiple":[34],"involves":[36],"pooling":[37],"data":[38],"from":[39],"several":[40],"during":[42],"building":[45],"single":[47],"model":[48,65,95,101,133],"multi-task":[50,75,99],"fashion,":[51],"where":[52,66],"tasks":[53],"correspond":[54],"individual":[56],"accents.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61,67],"explore":[62],"an":[63,70],"alternate":[64],"jointly":[68,126],"learn":[69],"accent":[71,129],"classifier":[72],"acoustic":[76,100,132],"model.":[77],"Experiments":[78],"on":[79,113,120],"American":[81,121],"English":[82,88],"Wall":[83],"Street":[84],"Journal":[85],"British":[87,114],"Cambridge":[89],"corpora":[90],"demonstrate":[91],"that":[92,125],"our":[93],"joint":[94],"outperforms":[96],"strong":[98],"baseline.":[102],"We":[103],"obtain":[104],"5.94%":[106],"relative":[107,118],"improvement":[108,119],"word":[110],"error":[111],"rate":[112],"English,":[115],"9.47%":[117],"English.":[122],"This":[123],"illustrates":[124],"modeling":[127],"information":[130],"improves":[131],"performance.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}