{"id":"https://openalex.org/W4372260202","doi":"https://doi.org/10.1109/icassp49357.2023.10096971","title":"Text is all You Need: Personalizing ASR Models Using Controllable Speech Synthesis","display_name":"Text is all You Need: Personalizing ASR Models Using Controllable Speech Synthesis","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260202","doi":"https://doi.org/10.1109/icassp49357.2023.10096971"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096971","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096971","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5062173174","display_name":"Karren Yang","orcid":"https://orcid.org/0000-0003-1885-5552"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Karren Yang","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062098630","display_name":"Ting-Yao Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ting-Yao Hu","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066816752","display_name":"Jen-Hao Rick Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jen-Hao Rick Chang","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064400393","display_name":"Hema Swetha Koppula","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hema Swetha Koppula","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028613002","display_name":"Oncel Tuzel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oncel Tuzel","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210107260"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"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/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":0.9976999759674072,"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":0.9933000206947327,"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/personalization","display_name":"Personalization","score":0.8295254111289978},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7989158034324646},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5571296215057373},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5515291690826416},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5166850090026855},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.45483914017677307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40644779801368713},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11968103051185608}],"concepts":[{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.8295254111289978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7989158034324646},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5571296215057373},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5515291690826416},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5166850090026855},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.45483914017677307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40644779801368713},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11968103051185608},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096971","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096971","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1989549063","https://openalex.org/W2010362084","https://openalex.org/W2079623482","https://openalex.org/W2239847623","https://openalex.org/W2764043458","https://openalex.org/W2890964092","https://openalex.org/W2912937645","https://openalex.org/W2962780374","https://openalex.org/W2972359262","https://openalex.org/W3006439955","https://openalex.org/W3007548213","https://openalex.org/W3007550212","https://openalex.org/W3008480565","https://openalex.org/W3015449694","https://openalex.org/W3015501067","https://openalex.org/W3015654635","https://openalex.org/W3016008406","https://openalex.org/W3080248383","https://openalex.org/W3097777922","https://openalex.org/W3101648800","https://openalex.org/W3112702554","https://openalex.org/W3125118953","https://openalex.org/W3147900189","https://openalex.org/W3171975124","https://openalex.org/W3197712601","https://openalex.org/W3205665014","https://openalex.org/W3208049241","https://openalex.org/W4286909631","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6745148473","https://openalex.org/W6774195376","https://openalex.org/W6785749098","https://openalex.org/W6792680588","https://openalex.org/W6796435857","https://openalex.org/W6802119844","https://openalex.org/W6917585676","https://openalex.org/W7027429494"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W2378211422","https://openalex.org/W2154063878","https://openalex.org/W4231274751","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W1538046993","https://openalex.org/W2571255492"],"abstract_inverted_index":{"Adapting":[0],"generic":[1],"speech":[2,67,134,139,179],"recognition":[3,68],"models":[4],"to":[5,13,71,137,168],"specific":[6],"individuals":[7],"is":[8,43,51,91,103,117,129,159],"a":[9,64,170],"challenging":[10],"problem":[11],"due":[12],"the":[14,24,59,100,106,111,114,121,149,153],"scarcity":[15],"of":[16,26,79,113,124,152],"personalized":[17,30,126],"data.":[18],"Recent":[19],"works":[20],"have":[21],"proposed":[22],"boosting":[23],"amount":[25],"training":[27],"data":[28,45,90,128,171],"using":[29],"text-to-speech":[31],"synthesis.":[32],"Here,":[33],"we":[34,62,131,146],"ask":[35],"two":[36],"fundamental":[37],"questions":[38],"about":[39],"this":[40],"strategy:":[41],"when":[42,98],"synthetic":[44,89,127,154],"effective":[46,53,92],"for":[47,161,174],"personalization,":[48],"and":[49,109,143],"why":[50,125],"it":[52],"in":[54,93,105],"those":[55],"cases?":[56],"To":[57,119],"address":[58,120],"first":[60],"question,":[61],"adapt":[63],"state-of-the-art":[65],"automatic":[66],"(ASR)":[69],"model":[70,116],"target":[72,101],"speakers":[73],"from":[74],"four":[75],"benchmark":[76],"datasets":[77],"representative":[78],"different":[80],"speaker":[81,102,162],"types.":[82],"We":[83],"show":[84],"that":[85,148],"ASR":[86,175],"personalization":[87,176],"with":[88,140],"all":[94],"cases,":[95],"but":[96],"particularly":[97],"(i)":[99],"underrepresented":[104],"global":[107,115],"data,":[108,155],"(ii)":[110],"capacity":[112],"limited.":[118],"second":[122],"question":[123],"effective,":[130],"use":[132],"controllable":[133],"synthesis":[135],"(CSS)":[136],"generate":[138],"varied":[141],"styles":[142],"content.":[144,180],"Surprisingly,":[145],"find":[147],"text":[150],"content":[151],"rather":[156],"than":[157],"style,":[158],"important":[160],"adaptation.":[163],"These":[164],"results":[165],"lead":[166],"us":[167],"propose":[169],"selection":[172],"strategy":[173],"based":[177],"on":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}