{"id":"https://openalex.org/W4408345944","doi":"https://doi.org/10.1109/icassp49660.2025.10887752","title":"persoDA: Personalized Data Augmentation for Personalized ASR","display_name":"persoDA: Personalized Data Augmentation for Personalized ASR","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345944","doi":"https://doi.org/10.1109/icassp49660.2025.10887752"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5060097629","display_name":"Pablo Peso Parada","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Pablo Peso Parada","raw_affiliation_strings":["Samsung R&D Institute UK (SRUK),United Kingdom"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute UK (SRUK),United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050650319","display_name":"Spyros Fontalis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Spyros Fontalis","raw_affiliation_strings":["Centre for Research and Technology,Hellas,Greece"],"affiliations":[{"raw_affiliation_string":"Centre for Research and Technology,Hellas,Greece","institution_ids":["https://openalex.org/I4210134249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113981675","display_name":"Md Asif Jalal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Md Asif Jalal","raw_affiliation_strings":["Samsung R&D Institute UK (SRUK),United Kingdom"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute UK (SRUK),United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113206703","display_name":"Karthikeyan Saravanan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Karthikeyan Saravanan","raw_affiliation_strings":["Samsung R&D Institute UK (SRUK),United Kingdom"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute UK (SRUK),United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109397355","display_name":"Anastasios Drosou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Anastasios Drosou","raw_affiliation_strings":["Centre for Research and Technology,Hellas,Greece"],"affiliations":[{"raw_affiliation_string":"Centre for Research and Technology,Hellas,Greece","institution_ids":["https://openalex.org/I4210134249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054882290","display_name":"Mete \u00d6zay","orcid":"https://orcid.org/0000-0002-7189-7260"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mete Ozay","raw_affiliation_strings":["Samsung R&D Institute UK (SRUK),United Kingdom"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute UK (SRUK),United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114121755","display_name":"Gil Ho Lee","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":"Gil Ho Lee","raw_affiliation_strings":["Language AI R&D Group(MX) Samsung Electronics,South Korea"],"affiliations":[{"raw_affiliation_string":"Language AI R&D Group(MX) Samsung Electronics,South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004902602","display_name":"Jungin Lee","orcid":"https://orcid.org/0000-0003-0390-119X"},"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":"Jungin Lee","raw_affiliation_strings":["Language AI R&D Group(MX) Samsung Electronics,South Korea"],"affiliations":[{"raw_affiliation_string":"Language AI R&D Group(MX) Samsung Electronics,South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057180394","display_name":"Seokyeong Jung","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":"Seokyeong Jung","raw_affiliation_strings":["Language AI R&D Group(MX) Samsung Electronics,South Korea"],"affiliations":[{"raw_affiliation_string":"Language AI R&D Group(MX) Samsung Electronics,South Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5060097629"],"corresponding_institution_ids":["https://openalex.org/I4210117523"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05660153,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.833899974822998,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.833899974822998,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.760200023651123,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.7092000246047974,"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":0.7581783533096313},{"id":"https://openalex.org/keywords/personalized-medicine","display_name":"Personalized medicine","score":0.42982199788093567},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.07185649871826172}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7581783533096313},{"id":"https://openalex.org/C32220436","wikidata":"https://www.wikidata.org/wiki/Q2072214","display_name":"Personalized medicine","level":2,"score":0.42982199788093567},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.07185649871826172},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1574170747","https://openalex.org/W1682403713","https://openalex.org/W2033288740","https://openalex.org/W2168961642","https://openalex.org/W2523573275","https://openalex.org/W2564008415","https://openalex.org/W2696967604","https://openalex.org/W2936774411","https://openalex.org/W2963040451","https://openalex.org/W3013948229","https://openalex.org/W3015522062","https://openalex.org/W3016008406","https://openalex.org/W3080248383","https://openalex.org/W3097777922","https://openalex.org/W3112702554","https://openalex.org/W3167533889","https://openalex.org/W3174329270","https://openalex.org/W3197223534","https://openalex.org/W3197227964","https://openalex.org/W3198769601","https://openalex.org/W3202725408","https://openalex.org/W3211278025","https://openalex.org/W4231225162","https://openalex.org/W4296069141","https://openalex.org/W4296069265","https://openalex.org/W4297841831","https://openalex.org/W4297841923","https://openalex.org/W4319862247","https://openalex.org/W4387682382","https://openalex.org/W6688816777","https://openalex.org/W6784764134"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,47,86,126],"(DA)":[2],"is":[3],"ubiquitously":[4],"used":[5],"in":[6,48],"training":[7,71],"of":[8,28,79],"Automatic":[9],"Speech":[10],"Recognition":[11],"(ASR)":[12],"models.":[13],"DA":[14,55],"offers":[15],"increased":[16],"data":[17,46,60,73,125],"variability,":[18],"robustness":[19],"and":[20,51,96,108],"generalization":[21],"against":[22],"different":[23],"acoustic":[24,77],"distortions.":[25],"Recently,":[26],"personalization":[27],"ASR":[29,64,102],"models":[30],"on":[31,88,106],"mobile":[32],"devices":[33],"has":[34],"been":[35],"shown":[36],"to":[37,62,69,84,136],"improve":[38],"Word":[39],"Error":[40],"Rate":[41],"(WER).":[42],"This":[43],"paper":[44],"evaluates":[45],"this":[49],"context":[50],"proposes":[52],"persoDA;":[53],"a":[54,117],"method":[56],"driven":[57],"by":[58],"user\u2019s":[59],"utilized":[61],"personalize":[63],"[1]":[65],"\u2013[3].":[66],"persoDA":[67,115,133],"aims":[68],"augment":[70],"with":[72,100],"specifically":[74],"tuned":[75],"towards":[76],"characteristics":[78],"the":[80],"end-user,":[81],"as":[82],"opposed":[83],"standard":[85,124],"based":[87],"Multi-Condition":[89],"Training":[90],"(MCT)":[91],"that":[92,114],"applies":[93],"random":[94,128],"reverberation":[95],"noises.":[97],"Our":[98],"evaluation":[99],"an":[101],"conformer-based":[103],"baseline":[104],"trained":[105],"Librispeech":[107],"per-sonalized":[109],"for":[110],"VOICES":[111],"[4]":[112],"shows":[113,134],"achieves":[116],"13.9%":[118],"relative":[119],"WER":[120],"reduction":[121],"over":[122,140],"using":[123],"(using":[127],"noise":[129],"&":[130],"reverberation).":[131],"Furthermore,":[132],"16%":[135],"20%":[137],"faster":[138],"convergence":[139],"MCT.":[141]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}