{"id":"https://openalex.org/W4372266927","doi":"https://doi.org/10.1109/icassp49357.2023.10094705","title":"Self-Supervised Learning for Speech Enhancement Through Synthesis","display_name":"Self-Supervised Learning for Speech Enhancement Through Synthesis","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266927","doi":"https://doi.org/10.1109/icassp49357.2023.10094705"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094705","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/A5078496422","display_name":"Bryce Irvin","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryce Irvin","raw_affiliation_strings":["Bose Corporation,USA","Bose Corporation, USA","Georgia Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation,USA","institution_ids":["https://openalex.org/I76587968"]},{"raw_affiliation_string":"Bose Corporation, USA","institution_ids":["https://openalex.org/I76587968"]},{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028041356","display_name":"Marko Stamenovic","orcid":null},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marko Stamenovic","raw_affiliation_strings":["Bose Corporation,USA","Bose Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation,USA","institution_ids":["https://openalex.org/I76587968"]},{"raw_affiliation_string":"Bose Corporation, USA","institution_ids":["https://openalex.org/I76587968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029632932","display_name":"Mikolaj Kegler","orcid":"https://orcid.org/0000-0003-3408-2588"},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mikolaj Kegler","raw_affiliation_strings":["Bose Corporation,USA","Bose Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation,USA","institution_ids":["https://openalex.org/I76587968"]},{"raw_affiliation_string":"Bose Corporation, USA","institution_ids":["https://openalex.org/I76587968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068970053","display_name":"Li-Chia Yang","orcid":"https://orcid.org/0000-0001-7342-6529"},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li-Chia Yang","raw_affiliation_strings":["Bose Corporation,USA","Bose Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation,USA","institution_ids":["https://openalex.org/I76587968"]},{"raw_affiliation_string":"Bose Corporation, USA","institution_ids":["https://openalex.org/I76587968"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"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/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":0.9991000294685364,"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":0.9980000257492065,"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":0.8236610889434814},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6992056369781494},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5955846309661865},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5605676770210266},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5067053437232971},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5064226388931274},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.46680334210395813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45433053374290466},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4325485825538635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8236610889434814},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6992056369781494},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5955846309661865},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5605676770210266},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5067053437232971},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5064226388931274},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.46680334210395813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45433053374290466},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4325485825538635},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094705","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/10","display_name":"Reduced inequalities","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1596515083","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2507009361","https://openalex.org/W2519091744","https://openalex.org/W2757519008","https://openalex.org/W2972443522","https://openalex.org/W3004597053","https://openalex.org/W3016181583","https://openalex.org/W3028019732","https://openalex.org/W3036601975","https://openalex.org/W3091570562","https://openalex.org/W3092028330","https://openalex.org/W3097906045","https://openalex.org/W3097945073","https://openalex.org/W3134695619","https://openalex.org/W3163296124","https://openalex.org/W3196475561","https://openalex.org/W3197580070","https://openalex.org/W3202667537","https://openalex.org/W3206252155","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3210530853","https://openalex.org/W4200483526","https://openalex.org/W4224933800","https://openalex.org/W4225302959","https://openalex.org/W4226403810","https://openalex.org/W4283652729","https://openalex.org/W4296069122","https://openalex.org/W4301371414","https://openalex.org/W4310873011","https://openalex.org/W6724944384","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6803547063","https://openalex.org/W6838724896"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W3208297503","https://openalex.org/W3119773509","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611","https://openalex.org/W2619127353"],"abstract_inverted_index":{"Modern":[0],"speech":[1,28,77],"enhancement":[2],"(SE)":[3],"networks":[4],"typically":[5],"implement":[6],"noise":[7],"suppression":[8],"through":[9],"time-frequency":[10],"masking,":[11,14],"latent":[12],"representation":[13],"or":[15],"discriminative":[16],"signal":[17],"prediction.":[18],"In":[19,46],"contrast,":[20],"some":[21],"recent":[22],"works":[23],"explore":[24],"SE":[25,145],"via":[26],"generative":[27],"synthesis,":[29],"where":[30,56],"the":[31,100],"system\u2019s":[32],"output":[33],"is":[34],"synthesized":[35],"by":[36],"a":[37,51,57,85,107],"neural":[38],"vocoder":[39,53,58,97],"after":[40],"an":[41,142],"inherently":[42],"lossy":[43],"feature-denoising":[44],"step.":[45],"this":[47],"paper,":[48],"we":[49,105,124],"propose":[50],"denoising":[52],"(DeVo)":[54],"approach,":[55],"accepts":[59],"noisy":[60],"representations":[61,72],"and":[62,93,119,129,140],"learns":[63],"to":[64,79,133],"directly":[65],"synthesize":[66],"clean":[67],"speech.":[68],"We":[69,83],"leverage":[70],"rich":[71],"from":[73],"self-supervised":[74],"learning":[75],"(SSL)":[76],"models":[78],"discover":[80],"relevant":[81],"features.":[82],"conduct":[84,125],"candidate":[86],"search":[87],"across":[88],"15":[89],"potential":[90],"SSL":[91,102],"front-ends":[92],"subsequently":[94],"train":[95],"our":[96,135],"adversarially":[98],"with":[99,116],"best":[101],"configuration.":[103],"Additionally,":[104],"demonstrate":[106],"causal":[108],"version":[109],"capable":[110],"of":[111],"running":[112],"on":[113],"streaming":[114],"audio":[115],"10ms":[117],"latency":[118],"minimal":[120],"performance":[121],"degradation.":[122],"Finally,":[123],"both":[126],"objective":[127,138],"evaluations":[128],"subjective":[130],"listening":[131],"studies":[132],"show":[134],"system":[136],"improves":[137],"metrics":[139],"outperforms":[141],"existing":[143],"state-of-the-art":[144],"model":[146],"subjectively.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}