{"id":"https://openalex.org/W4410771164","doi":"https://doi.org/10.1109/icasspw65056.2025.11011159","title":"Generative Data Augmentation Challenge: Zero-Shot Speech Synthesis for Personalized Speech Enhancement","display_name":"Generative Data Augmentation Challenge: Zero-Shot Speech Synthesis for Personalized Speech Enhancement","publication_year":2025,"publication_date":"2025-04-06","ids":{"openalex":"https://openalex.org/W4410771164","doi":"https://doi.org/10.1109/icasspw65056.2025.11011159"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw65056.2025.11011159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5060429696","display_name":"Jae\u2010sung Bae","orcid":"https://orcid.org/0000-0002-8270-0072"},"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":"Jae-Sung Bae","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055422970","display_name":"Anastasia Kuznetsova","orcid":null},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anastasia Kuznetsova","raw_affiliation_strings":["Indiana University"],"affiliations":[{"raw_affiliation_string":"Indiana University","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":["University of Maryland"],"affiliations":[{"raw_affiliation_string":"University of Maryland","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","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":"John Hershey","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075577786","display_name":"Trausti Kristjansson","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trausti Kristjansson","raw_affiliation_strings":["Amazon Lab126"],"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064582903","display_name":"Minje Kim","orcid":"https://orcid.org/0000-0003-3513-8328"},"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":"Minje Kim","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5060429696"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":5.7685,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95514849,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"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":0.9969000220298767,"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":0.9969000220298767,"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":0.9969000220298767,"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":0.9228000044822693,"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/computer-science","display_name":"Computer science","score":0.6965488791465759},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.672680139541626},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6369990110397339},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6186521649360657},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5146782994270325},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4763491451740265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38065236806869507},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3672860264778137},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08382382988929749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6965488791465759},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.672680139541626},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6369990110397339},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6186521649360657},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5146782994270325},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4763491451740265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38065236806869507},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3672860264778137},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08382382988929749},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw65056.2025.11011159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W2067295501","https://openalex.org/W2127851351","https://openalex.org/W2936774411","https://openalex.org/W2952218014","https://openalex.org/W2954996726","https://openalex.org/W2972359262","https://openalex.org/W3047992192","https://openalex.org/W3167533889","https://openalex.org/W3196475561","https://openalex.org/W3197912330","https://openalex.org/W3205644108","https://openalex.org/W4205689591","https://openalex.org/W4225309689","https://openalex.org/W4285258106","https://openalex.org/W4372260202","https://openalex.org/W4372262450","https://openalex.org/W4372269365","https://openalex.org/W4391021724","https://openalex.org/W4392902644","https://openalex.org/W4393380352","https://openalex.org/W4402112533","https://openalex.org/W6631190155","https://openalex.org/W6688816777","https://openalex.org/W6796464841","https://openalex.org/W6805710207","https://openalex.org/W6847363464","https://openalex.org/W6848735303","https://openalex.org/W6850312524","https://openalex.org/W6852421699","https://openalex.org/W6862144568","https://openalex.org/W6872403736","https://openalex.org/W6873568948","https://openalex.org/W6873666011"],"related_works":["https://openalex.org/W2380075625","https://openalex.org/W4390718435","https://openalex.org/W4390549206","https://openalex.org/W3137171911","https://openalex.org/W4379540039","https://openalex.org/W4237784285","https://openalex.org/W2374712251","https://openalex.org/W1630865680","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3],"new":[4],"challenge":[5],"that":[6],"calls":[7],"for":[8,17],"zero-shot":[9,79,114,128],"text-to-speech":[10],"(TTS)":[11],"systems":[12,81,88],"to":[13,43,82,91,104,131],"augment":[14,83],"speech":[15,22],"data":[16,39,61,111],"the":[18,28,53,107],"downstream":[19],"task,":[20],"personalized":[21,38,84,97],"enhancement":[23],"(PSE),":[24],"as":[25],"part":[26],"of":[27,109],"Generative":[29],"Data":[30],"Augmentation":[31],"workshop":[32],"at":[33],"ICASSP":[34],"2025.":[35],"Collecting":[36],"high-quality":[37],"is":[40],"challenging":[41],"due":[42],"privacy":[44],"concerns":[45],"and":[46,134,141],"technical":[47],"difficulties":[48],"in":[49],"recording":[50],"audio":[51],"from":[52],"test":[54],"scene.":[55],"To":[56],"address":[57],"these":[58],"issues,":[59],"synthetic":[60],"generation":[62],"using":[63,126],"generative":[64],"models":[65,116,130],"has":[66],"gained":[67],"significant":[68],"attention.":[69],"In":[70],"this":[71,95,100],"challenge,":[72,101],"participants":[73],"are":[74,89,143],"tasked":[75],"first":[76],"with":[77,94],"building":[78],"TTS":[80,115,129],"data.":[85],"Subsequently,":[86],"PSE":[87,118],"asked":[90],"be":[92],"trained":[93],"augmented":[96,110],"dataset.":[98],"Through":[99],"we":[102],"aim":[103],"investigate":[105],"how":[106],"quality":[108],"generated":[112],"by":[113],"affects":[117],"model":[119],"performance.":[120],"We":[121],"also":[122],"provide":[123],"baseline":[124,138],"experiments":[125],"open-source":[127],"encourage":[132],"participation":[133],"benchmark":[135],"advancements.":[136],"Our":[137],"code":[139],"implementation":[140],"checkpoints":[142],"available":[144],"online<sup":[145],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[146],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}