{"id":"https://openalex.org/W4372269365","doi":"https://doi.org/10.1109/icassp49357.2023.10096601","title":"The Potential of Neural Speech Synthesis-Based Data Augmentation for Personalized Speech Enhancement","display_name":"The Potential of Neural Speech Synthesis-Based Data Augmentation for Personalized Speech Enhancement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372269365","doi":"https://doi.org/10.1109/icassp49357.2023.10096601"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096601","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":"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/A5055422970","display_name":"Anastasia Kuznetsova","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anastasia Kuznetsova","raw_affiliation_strings":["Indiana University,Luddy School of Informatics, Computing, and Engineering,Bloomington,IN,USA","Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University,Luddy School of Informatics, Computing, and Engineering,Bloomington,IN,USA","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085011950","display_name":"Aswin Sivaraman","orcid":"https://orcid.org/0000-0003-2248-4846"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aswin Sivaraman","raw_affiliation_strings":["Indiana University,Luddy School of Informatics, Computing, and Engineering,Bloomington,IN,USA","Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University,Luddy School of Informatics, Computing, and Engineering,Bloomington,IN,USA","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"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/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minje Kim","raw_affiliation_strings":["Indiana University,Luddy School of Informatics, Computing, and Engineering,Bloomington,IN,USA","Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University,Luddy School of Informatics, Computing, and Engineering,Bloomington,IN,USA","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055422970"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":1.2199,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78675596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8493841886520386},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.7724292874336243},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7180240154266357},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5658699870109558},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5321290493011475},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.46665310859680176},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.46148672699928284},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45488882064819336},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.45215484499931335},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.43619537353515625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4302862286567688},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33436018228530884},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07553082704544067}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8493841886520386},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.7724292874336243},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7180240154266357},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5658699870109558},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5321290493011475},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.46665310859680176},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46148672699928284},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45488882064819336},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.45215484499931335},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.43619537353515625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4302862286567688},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33436018228530884},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07553082704544067},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096601","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W2067295501","https://openalex.org/W2078528584","https://openalex.org/W2127851351","https://openalex.org/W2140147143","https://openalex.org/W2219249508","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963341071","https://openalex.org/W2973062255","https://openalex.org/W2998572311","https://openalex.org/W3008480565","https://openalex.org/W3095717210","https://openalex.org/W3096408984","https://openalex.org/W3097911996","https://openalex.org/W3099330747","https://openalex.org/W3142516134","https://openalex.org/W3162424266","https://openalex.org/W3162538144","https://openalex.org/W3167533889","https://openalex.org/W3196475561","https://openalex.org/W3198543387","https://openalex.org/W3206706278","https://openalex.org/W4225680573","https://openalex.org/W4285258106","https://openalex.org/W4381786045","https://openalex.org/W6631190155","https://openalex.org/W6688816777","https://openalex.org/W6755462816","https://openalex.org/W6772349387","https://openalex.org/W6805710207","https://openalex.org/W6843330092"],"related_works":["https://openalex.org/W2109940557","https://openalex.org/W2466832359","https://openalex.org/W3172493050","https://openalex.org/W1582019636","https://openalex.org/W1499005795","https://openalex.org/W2593798266","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W3208304128"],"abstract_inverted_index":{"With":[0],"the":[1,76,82,90,102,108,111,123,131,136,149],"advances":[2],"in":[3,27,40],"deep":[4],"learning,":[5],"speech":[6,49,58,98],"enhancement":[7,50,59,150],"systems":[8,142],"benefited":[9],"from":[10],"large":[11],"neural":[12,97],"network":[13],"architectures":[14],"and":[15,31,56,117],"achieved":[16],"state-of-the-art":[17],"quality.":[18,151],"However,":[19],"speaker-agnostic":[20,137],"methods":[21],"are":[22,36,120],"not":[23],"always":[24],"desirable,":[25],"both":[26],"terms":[28],"of":[29,85,92,110],"quality":[30,109],"their":[32],"complexity,":[33],"when":[34],"they":[35,119],"to":[37,64,129],"be":[38,127],"used":[39,128],"a":[41,54,70],"resource-constrained":[42],"environment.":[43],"One":[44],"promising":[45],"way":[46],"is":[47,53],"personalized":[48],"(PSE),":[51],"which":[52],"smaller":[55],"easier":[57],"problem":[60],"for":[61],"small":[62],"models":[63],"solve,":[65],"because":[66],"it":[67],"focuses":[68],"on":[69,96],"particular":[71],"test-time":[72],"user.":[73],"To":[74],"achieve":[75],"personalization":[77],"goal,":[78],"while":[79,147],"dealing":[80],"with":[81],"typical":[83],"lack":[84],"personal":[86],"data,":[87],"we":[88,105],"investigate":[89],"effect":[91],"data":[93,115],"augmentation":[94],"based":[95],"synthesis":[99],"(NSS).":[100],"In":[101],"proposed":[103,140],"method,":[104],"show":[106,143],"that":[107,134],"NSS":[112],"system\u2019s":[113],"synthetic":[114],"matters,":[116],"if":[118],"good":[121],"enough":[122],"augmented":[124],"dataset":[125],"can":[126],"improve":[130],"PSE":[132,141],"system":[133],"outperforms":[135],"baseline.":[138],"The":[139],"significant":[144],"complexity":[145],"reduction":[146],"preserving":[148]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}