{"id":"https://openalex.org/W4392902995","doi":"https://doi.org/10.1109/icassp48485.2024.10446344","title":"Unsupervised Accent Adaptation Through Masked Language Model Correction of Discrete Self-Supervised Speech Units","display_name":"Unsupervised Accent Adaptation Through Masked Language Model Correction of Discrete Self-Supervised Speech Units","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902995","doi":"https://doi.org/10.1109/icassp48485.2024.10446344"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446344","doi":"https://doi.org/10.1109/icassp48485.2024.10446344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446344","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.13994","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009033650","display_name":"Jakob Poncelet","orcid":"https://orcid.org/0000-0002-5157-7577","observed_orcids":["https://orcid.org/0000-0002-5157-7577"]},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Jakob Poncelet","raw_affiliation_strings":["KU Leuven,Department Electrical Engineering ESAT-PSI,Leuven,Belgium","Department Electrical Engineering ESAT-PSI, KU Leuven, Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KU Leuven,Department Electrical Engineering ESAT-PSI,Leuven,Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"Department Electrical Engineering ESAT-PSI, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087514947","display_name":"Hugo Van hamme","orcid":"https://orcid.org/0000-0003-1331-5186","observed_orcids":["https://orcid.org/0000-0003-1331-5186"]},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Hugo Van Hamme","raw_affiliation_strings":["KU Leuven,Department Electrical Engineering ESAT-PSI,Leuven,Belgium","Department Electrical Engineering ESAT-PSI, KU Leuven, Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KU Leuven,Department Electrical Engineering ESAT-PSI,Leuven,Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"Department Electrical Engineering ESAT-PSI, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99464096"],"apc_list":null,"apc_paid":null,"fwci":0.6108,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68601491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"10236","last_page":"10240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.0003000000142492354,"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/T10403","display_name":"Phonetics and Phonology Research","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/accent-adaptation","display_name":"accent adaptation","score":0.9700000286102295},{"id":"https://openalex.org/keywords/unsupervised-adaptation","display_name":"unsupervised adaptation","score":0.6489999890327454},{"id":"https://openalex.org/keywords/masked-language-models","display_name":"masked language models","score":0.7490000128746033},{"id":"https://openalex.org/keywords/self-supervised-speech-representation-learning","display_name":"self-supervised speech representation learning","score":0.7870000004768372},{"id":"https://openalex.org/keywords/hubert","display_name":"HuBERT","score":0.7580000162124634},{"id":"https://openalex.org/keywords/accent-robustness","display_name":"accent robustness","score":0.777999997138977},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.45899999141693115},{"id":"https://openalex.org/keywords/domain-shift","display_name":"domain shift","score":0.47200000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7583180665969849},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.719543993473053},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5801476240158081},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.531721830368042},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5287401676177979},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5270968675613403},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5163286924362183},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.515661358833313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49800896644592285},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.43184950947761536},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4288630485534668},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36420565843582153},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.35134410858154297},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09323588013648987},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446344","doi":"https://doi.org/10.1109/icassp48485.2024.10446344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446344","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2309.13994","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.13994","pdf_url":"https://arxiv.org/pdf/2309.13994","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:lirias2repo.kuleuven.be:20.500.12942/740878","doi":null,"is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/740878","pdf_url":"https://lirias.kuleuven.be/retrieve/934e2e43-d178-40db-b265-264f3b05840e","source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"49th IEEE international conference on acoustics, speech, and signal processing - ICASSP 2024, Seoul, Korea, 14-19 April 2024","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2309.13994","doi":"https://doi.org/10.48550/arxiv.2309.13994","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2309.13994","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.13994","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.13994","pdf_url":"https://arxiv.org/pdf/2309.13994","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392902995.pdf","grobid_xml":"https://content.openalex.org/works/W4392902995.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W659550629","https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2913946806","https://openalex.org/W2937808806","https://openalex.org/W2962753370","https://openalex.org/W2963341956","https://openalex.org/W2978017171","https://openalex.org/W2995929068","https://openalex.org/W3015356564","https://openalex.org/W3015723617","https://openalex.org/W3097882114","https://openalex.org/W3129009457","https://openalex.org/W3144173820","https://openalex.org/W3160475509","https://openalex.org/W3162812479","https://openalex.org/W3163596720","https://openalex.org/W3165666670","https://openalex.org/W3169320628","https://openalex.org/W3197580070","https://openalex.org/W3209984917","https://openalex.org/W4221161761","https://openalex.org/W4226033575","https://openalex.org/W4283659485","https://openalex.org/W4292387508","https://openalex.org/W4319862412","https://openalex.org/W4375868763","https://openalex.org/W4385567350","https://openalex.org/W4385822676","https://openalex.org/W4385822683","https://openalex.org/W4385823170","https://openalex.org/W6769196770","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W7167498076","https://openalex.org/W7166464730","https://openalex.org/W4385823170","https://openalex.org/W4402111809","https://openalex.org/W2180936379","https://openalex.org/W7204542339","https://openalex.org/W7134245636","https://openalex.org/W3197561413","https://openalex.org/W4375869215","https://openalex.org/W2294933947"],"abstract_inverted_index":{"Self-supervised":[0],"pre-trained":[1,94,111],"speech":[2,7,46,135],"models":[3,25],"have":[4],"strongly":[5],"improved":[6],"recognition,":[8],"yet":[9],"they":[10],"are":[11,90,122],"still":[12],"sensitive":[13],"to":[14,31,38,48,105,124],"domain":[15],"shifts":[16],"and":[17,69,81,96,117],"accented":[18,45,73,134],"or":[19,29],"atypical":[20],"speech.":[21],"Many":[22],"of":[23,109],"these":[24],"rely":[26],"on":[27,62,131],"quantisation":[28],"clustering":[30],"learn":[32],"discrete":[33,42,63],"acoustic":[34],"units.":[35],"We":[36,121],"propose":[37],"correct":[39],"the":[40,93,100,110,140,144],"discovered":[41],"units":[43,64],"for":[44],"back":[47],"a":[49,66,114,126,132],"standard":[50,67],"pronunciation":[51],"in":[52,92],"an":[53,72,106],"unsupervised":[54],"manner.":[55],"A":[56],"masked":[57],"language":[58],"model":[59,95,112,130],"is":[60],"trained":[61],"from":[65],"accent":[68,87],"iteratively":[70],"corrects":[71],"token":[74],"sequence":[75],"by":[76,98,138],"masking":[77],"unexpected":[78],"cluster":[79],"sequences":[80],"predicting":[82,99],"their":[83],"common":[84],"variant.":[85],"Small":[86],"adapter":[88],"blocks":[89],"inserted":[91],"fine-tuned":[97],"corrected":[101],"clusters,":[102],"which":[103],"leads":[104],"increased":[107],"robustness":[108],"towards":[113],"target":[115],"accent,":[116],"this":[118],"without":[119],"supervision.":[120],"able":[123],"improve":[125],"state-of-the-art":[127],"HuBERT":[128],"Large":[129],"downstream":[133],"recognition":[136],"task":[137],"altering":[139],"training":[141],"regime":[142],"with":[143],"proposed":[145],"method.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-03-19T00:00:00"}