{"id":"https://openalex.org/W4285258106","doi":"https://doi.org/10.1109/jstsp.2022.3181782","title":"Efficient Personalized Speech Enhancement Through Self-Supervised Learning","display_name":"Efficient Personalized Speech Enhancement Through Self-Supervised Learning","publication_year":2022,"publication_date":"2022-06-13","ids":{"openalex":"https://openalex.org/W4285258106","doi":"https://doi.org/10.1109/jstsp.2022.3181782"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2022.3181782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3181782","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.02017","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":["Department of Intelligent Systems Engineering, Indiana University Bloomington, Bloomington, IN, USA"],"raw_orcid":"https://orcid.org/0000-0003-2248-4846","affiliations":[{"raw_affiliation_string":"Department of Intelligent Systems Engineering, Indiana University Bloomington, 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":["Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, USA"],"raw_orcid":"https://orcid.org/0000-0003-3513-8328","affiliations":[{"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":null,"fwci":2.9286,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.91878049,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"16","issue":"6","first_page":"1342","last_page":"1356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9986000061035156,"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":0.8361674547195435},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.7643063068389893},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.5376670360565186},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5349112153053284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5222957134246826},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.502260684967041},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5016248226165771},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4716424345970154},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09310689568519592},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.08481153845787048}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8361674547195435},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.7643063068389893},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.5376670360565186},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5349112153053284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5222957134246826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.502260684967041},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5016248226165771},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4716424345970154},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09310689568519592},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.08481153845787048},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstsp.2022.3181782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3181782","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2104.02017","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.02017","pdf_url":"https://arxiv.org/pdf/2104.02017","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,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.02017","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.02017","pdf_url":"https://arxiv.org/pdf/2104.02017","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,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3623532510","display_name":null,"funder_award_id":"2046963","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1790748249","https://openalex.org/W1897240248","https://openalex.org/W2067149324","https://openalex.org/W2067295501","https://openalex.org/W2078528584","https://openalex.org/W2127851351","https://openalex.org/W2150341604","https://openalex.org/W2160815625","https://openalex.org/W2219249508","https://openalex.org/W2221409856","https://openalex.org/W2312966647","https://openalex.org/W2403380333","https://openalex.org/W2550397165","https://openalex.org/W2593116425","https://openalex.org/W2711861986","https://openalex.org/W2807396610","https://openalex.org/W2808706139","https://openalex.org/W2889442120","https://openalex.org/W2889885720","https://openalex.org/W2896457183","https://openalex.org/W2899508538","https://openalex.org/W2938874599","https://openalex.org/W2949756029","https://openalex.org/W2950865323","https://openalex.org/W2951786554","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963163009","https://openalex.org/W2963341071","https://openalex.org/W2963426332","https://openalex.org/W2963443859","https://openalex.org/W2963452667","https://openalex.org/W2963853675","https://openalex.org/W2963961268","https://openalex.org/W2973062255","https://openalex.org/W3005680577","https://openalex.org/W3015544941","https://openalex.org/W3016912202","https://openalex.org/W3031202003","https://openalex.org/W3035837245","https://openalex.org/W3093839391","https://openalex.org/W3095717210","https://openalex.org/W3097911996","https://openalex.org/W3099330747","https://openalex.org/W3122264812","https://openalex.org/W3124794156","https://openalex.org/W3161266072","https://openalex.org/W3162424266","https://openalex.org/W3162538144","https://openalex.org/W3162577490","https://openalex.org/W3163114796","https://openalex.org/W3164223074","https://openalex.org/W3197227964","https://openalex.org/W3198543387","https://openalex.org/W3206116612","https://openalex.org/W3206706278","https://openalex.org/W4205483086","https://openalex.org/W4205689591","https://openalex.org/W4205947740","https://openalex.org/W4287632494","https://openalex.org/W4295122182","https://openalex.org/W4295312788","https://openalex.org/W4297775537","https://openalex.org/W4297813615","https://openalex.org/W4324109905","https://openalex.org/W6631190155","https://openalex.org/W6677580257","https://openalex.org/W6688816777","https://openalex.org/W6713339159","https://openalex.org/W6735374517","https://openalex.org/W6737664043","https://openalex.org/W6751512325","https://openalex.org/W6752888775","https://openalex.org/W6756257017","https://openalex.org/W6757632829","https://openalex.org/W6774314701","https://openalex.org/W6778691839","https://openalex.org/W6779216093","https://openalex.org/W6784499681","https://openalex.org/W6795747053"],"related_works":["https://openalex.org/W2109940557","https://openalex.org/W2466832359","https://openalex.org/W4391210591","https://openalex.org/W1582019636","https://openalex.org/W1499005795","https://openalex.org/W3172493050","https://openalex.org/W4385420271","https://openalex.org/W4312192618","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"self-supervised":[3,115,157],"learning":[4,94,116,158,188,206],"methods":[5,53,117,130,192,213],"for":[6,107],"monaural":[7],"speaker-specific":[8],"(i.e.,":[9,139],"personalized)":[10],"speech":[11,58,84,105,134,165,179],"enhancement":[12,166,200,235],"models.":[13],"While":[14],"general-purpose":[15],"models":[16,23,175],"must":[17],"broadly":[18],"address":[19],"many":[20],"speakers,":[21],"personalized":[22,133],"can":[24,39,54],"adapt":[25],"to":[26,32,46,65,98,121,176,220],"a":[27,34,77,92,119,163,169],"particular":[28],"speaker's":[29],"voice,":[30],"expecting":[31],"solve":[33],"narrower":[35],"problem.":[36],"Hence,":[37],"personalization":[38,52,74,126,230],"achieve":[40],"more":[41],"optimal":[42],"performance":[43],"in":[44,80],"addition":[45],"reducing":[47],"computational":[48],"complexity.":[49],"However,":[50],"naive":[51],"inconveniently":[55],"require":[56],"clean":[57,83,104,151,185,243],"from":[59,136,143,149,207,245],"the":[60,86,100,103,132,144,150,174,184,194,198,203,216,232,246],"target":[61,87,145,223,247],"user,":[62],"e.g.,":[63],"due":[64],"subpar":[66],"recording":[67],"conditions.":[68],"To":[69],"this":[70,111],"end,":[71],"we":[72,113],"pose":[73],"as":[75,118,168,180],"either":[76],"zero-shot":[78],"task,":[79,95,171],"which":[81,96,172],"no":[82],"of":[85,102,197,205],"speaker":[88],"is":[89,97],"used,":[90],"or":[91],"few-shot":[93,125],"minimize":[99],"duration":[101],"used":[106],"transfer":[108],"learning.":[109],"With":[110],"paper,":[112],"propose":[114],"solution":[120],"both":[122],"zero-":[123],"and":[124,189,241],"tasks.":[127],"The":[128,225],"proposed":[129],"learn":[131],"features":[135],"unlabeled":[137,208],"data":[138,190,244],"in-the-wild":[140],"noisy":[141,178],"recordings":[142],"user)":[146],"rather":[147],"than":[148],"sources.":[152],"We":[153,160,210],"investigate":[154],"three":[155],"different":[156,222],"mechanisms.":[159],"set":[161],"up":[162],"pseudo":[164,199],"problem":[167],"pretext":[170],"pretrains":[173],"estimate":[177],"if":[181],"it":[182],"were":[183],"target.":[186],"Contrastive":[187],"purification":[191],"regularize":[193],"loss":[195],"function":[196],"problem,":[201],"overcoming":[202],"limitations":[204],"data.":[209],"assess":[211],"our":[212],"by":[214],"personalizing":[215],"well-known":[217],"ConvTasNet":[218],"architecture":[219],"twenty":[221],"speakers.":[224],"results":[226],"show":[227],"that":[228],"self-supervision-based":[229],"improves":[231],"original":[233],"ConvTasNet's":[234],"quality":[236],"with":[237],"fewer":[238],"model":[239],"parameters":[240],"less":[242],"user.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2022-07-14T00:00:00"}