{"id":"https://openalex.org/W3211944253","doi":"https://doi.org/10.21437/interspeech.2022-10283","title":"OSSEM: one-shot speaker adaptive speech enhancement using meta learning","display_name":"OSSEM: one-shot speaker adaptive speech enhancement using meta learning","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W3211944253","doi":"https://doi.org/10.21437/interspeech.2022-10283","mag":"3211944253"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10283","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10283","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5058798840","display_name":"Cheng Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng Yu","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071471469","display_name":"Szu\u2010Wei Fu","orcid":"https://orcid.org/0000-0002-3487-8212"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Szu-wei Fu","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060785253","display_name":"Tsun-An Hsieh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tsun-An Hsieh","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040811098","display_name":"Mirco Ravanelli","orcid":"https://orcid.org/0000-0002-3929-5526"},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mirco Ravanelli","raw_affiliation_strings":["Mila-Quebec AI Institute, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila-Quebec AI Institute, Montreal, Canada","institution_ids":["https://openalex.org/I4210164802"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1074,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77362124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"981","last_page":"985"},"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":0.9998000264167786,"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":0.9977999925613403,"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":0.751439094543457},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6970497369766235},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6625495553016663},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6234639286994934},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6063668727874756},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.5953384041786194},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5028254389762878},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37282314896583557},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10187956690788269},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.08366313576698303},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.05872035026550293},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.04323399066925049}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.751439094543457},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6970497369766235},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6625495553016663},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6234639286994934},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6063668727874756},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.5953384041786194},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5028254389762878},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37282314896583557},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10187956690788269},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.08366313576698303},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.05872035026550293},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.04323399066925049},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10283","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10283","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2023673090","https://openalex.org/W2078528584","https://openalex.org/W2121973264","https://openalex.org/W2129092579","https://openalex.org/W2153894152","https://openalex.org/W2279798675","https://openalex.org/W2403766732","https://openalex.org/W2405774341","https://openalex.org/W2516342150","https://openalex.org/W2550397165","https://openalex.org/W2604763608","https://openalex.org/W2605589342","https://openalex.org/W2622263826","https://openalex.org/W2746457594","https://openalex.org/W2757519008","https://openalex.org/W2889442120","https://openalex.org/W2963303956","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2963403868","https://openalex.org/W2972425344","https://openalex.org/W2973016613","https://openalex.org/W2973220283","https://openalex.org/W2995049146","https://openalex.org/W3015474227","https://openalex.org/W3015585292","https://openalex.org/W3016129867","https://openalex.org/W3024869864","https://openalex.org/W3027637851","https://openalex.org/W3080158507","https://openalex.org/W3088775906","https://openalex.org/W3091830790","https://openalex.org/W3096643087","https://openalex.org/W3097945073","https://openalex.org/W3112462122","https://openalex.org/W3129467116","https://openalex.org/W3132954452","https://openalex.org/W3140741782","https://openalex.org/W3147539069","https://openalex.org/W3162538144","https://openalex.org/W3167533889","https://openalex.org/W3198613941","https://openalex.org/W4205483086","https://openalex.org/W4324109905","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"Although":[0],"deep":[1],"learning":[2],"(DL)":[3],"has":[4],"achieved":[5],"notable":[6],"progress":[7],"in":[8,49,95,128],"speech":[9],"enhancement":[10,123],"(SE),":[11],"further":[12],"research":[13],"is":[14],"still":[15],"required":[16],"for":[17,105,114],"a":[18,34,50,55,61,90,137,149,154,168],"DL-based":[19],"SE":[20,38,46,58,139,151,164,175],"system":[21],"to":[22,27,44,78,125,135,153,172],"adapt":[23,148],"effectively":[24,147],"and":[25,60,108,131],"efficiently":[26],"particular":[28,155],"speakers.In":[29],"this":[30],"study,":[31],"we":[32,88,118],"propose":[33],"novel":[35],"meta-learning-based":[36],"speaker-adaptive":[37],"approach":[39],"(called":[40],"OSSEM)":[41],"that":[42,144],"aims":[43],"achieve":[45],"model":[47,106,152],"adaptation":[48],"one-shot":[51],"manner.OSSEM":[52],"consists":[53],"of":[54],"modified":[56,91],"transformer":[57],"network":[59,69],"speaker-specific":[62],"masking":[63],"(SSM)":[64],"network.In":[65],"practice,":[66],"the":[67,80,100,109,116,122],"SSM":[68],"takes":[70],"an":[71],"enrolled":[72],"speaker":[73,156],"embedding":[74],"extracted":[75],"using":[76],"ECAPA-TDNN":[77],"adjust":[79],"input":[81],"noisy":[82],"feature":[83],"through":[84],"masking.To":[85],"evaluate":[86],"OSSEM,":[87],"designed":[89,133],"Voice":[92],"Bank-DEMAND":[93],"dataset,":[94],"which":[96],"one":[97,159],"utterance":[98],"from":[99],"testing":[101,115],"set":[102,119],"was":[103],"used":[104,113],"adaptation,":[107],"remaining":[110],"utterances":[111],"were":[112],"performance.Moreover,":[117],"restrictions":[120],"allowing":[121],"process":[124],"be":[126,136],"conducted":[127],"real":[129],"time,":[130],"thus":[132,161],"OSSEM":[134,145,166],"causal":[138,174],"system.Experimental":[140],"results":[141],"first":[142],"show":[143],"can":[146],"pretrained":[150],"with":[157],"only":[158],"utterance,":[160],"yielding":[162],"improved":[163],"results.Meanwhile,":[165],"exhibits":[167],"competitive":[169],"performance":[170],"compared":[171],"state-of-the-art":[173],"systems.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}