{"id":"https://openalex.org/W4319862462","doi":"https://doi.org/10.1109/slt54892.2023.10023356","title":"Exploring WavLM on Speech Enhancement","display_name":"Exploring WavLM on Speech Enhancement","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862462","doi":"https://doi.org/10.1109/slt54892.2023.10023356"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023356","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5073806960","display_name":"Hyungchan Song","orcid":"https://orcid.org/0000-0001-7847-1118"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyungchan Song","raw_affiliation_strings":["Gwanju Institute of Science and Technology,Republic of Korea","Gwanju Institute of Science and Technology, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Gwanju Institute of Science and Technology,Republic of Korea","institution_ids":["https://openalex.org/I39534123"]},{"raw_affiliation_string":"Gwanju Institute of Science and Technology, Republic of Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079533447","display_name":"Sanyuan Chen","orcid":"https://orcid.org/0000-0002-3082-6052"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sanyuan Chen","raw_affiliation_strings":["Microsoft,China","Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Microsoft,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345092","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-9011-7928"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft,USA","Microsoft, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324098","display_name":"Yu Wu","orcid":"https://orcid.org/0000-0002-1680-8253"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wu","raw_affiliation_strings":["Microsoft,China","Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Microsoft,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft,USA","Microsoft, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106627865","display_name":"Min Tang","orcid":"https://orcid.org/0009-0006-3428-9967"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Tang","raw_affiliation_strings":["Microsoft,USA","Microsoft, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054155133","display_name":"Jong Won Shin","orcid":"https://orcid.org/0000-0002-8910-0264"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jong Won Shin","raw_affiliation_strings":["Gwanju Institute of Science and Technology,Republic of Korea","Gwanju Institute of Science and Technology, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Gwanju Institute of Science and Technology,Republic of Korea","institution_ids":["https://openalex.org/I39534123"]},{"raw_affiliation_string":"Gwanju Institute of Science and Technology, Republic of Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-0785-8882"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":["Microsoft,China","Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Microsoft,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5073806960"],"corresponding_institution_ids":["https://openalex.org/I39534123"],"apc_list":null,"apc_paid":null,"fwci":0.7674,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.85534591,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"451","last_page":"457"},"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":0.9994999766349792,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8276796936988831},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.705073356628418},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6744251847267151},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5876429677009583},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5630687475204468},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.47238659858703613},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.44798994064331055},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4336376190185547},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4307451844215393},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42766863107681274},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39954301714897156},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.23691204190254211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8276796936988831},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.705073356628418},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6744251847267151},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5876429677009583},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5630687475204468},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.47238659858703613},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.44798994064331055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4336376190185547},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4307451844215393},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42766863107681274},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39954301714897156},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.23691204190254211},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023356","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2770119437","https://openalex.org/W2896457183","https://openalex.org/W2973049979","https://openalex.org/W2995181338","https://openalex.org/W3015337486","https://openalex.org/W3031135612","https://openalex.org/W3035837245","https://openalex.org/W3036601975","https://openalex.org/W3093839391","https://openalex.org/W3096408984","https://openalex.org/W3097945073","https://openalex.org/W3126648213","https://openalex.org/W3160129476","https://openalex.org/W3163842642","https://openalex.org/W3175898847","https://openalex.org/W3178203035","https://openalex.org/W3191448984","https://openalex.org/W3196614065","https://openalex.org/W3197042120","https://openalex.org/W3197580070","https://openalex.org/W3197729725","https://openalex.org/W3198680319","https://openalex.org/W3206252155","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4225302959","https://openalex.org/W4226033575","https://openalex.org/W4285258106","https://openalex.org/W4292969786","https://openalex.org/W4385245566","https://openalex.org/W6746278845","https://openalex.org/W6769196770","https://openalex.org/W6779216093","https://openalex.org/W6780218876","https://openalex.org/W6784499681","https://openalex.org/W6788335241","https://openalex.org/W6790299203","https://openalex.org/W6797992114"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2401089611","https://openalex.org/W2955597484","https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2373767407","https://openalex.org/W3110551121","https://openalex.org/W2131486661","https://openalex.org/W4200596008"],"abstract_inverted_index":{"There":[0],"is":[1,135],"a":[2,52,72,78,97],"surge":[3],"in":[4,6,14,45,109],"interest":[5],"self-supervised":[7,39],"learning":[8,40],"approaches":[9],"for":[10,42,120],"end-to-end":[11],"speech":[12,30,43,66,106,113,116],"encoding":[13],"recent":[15],"years":[16],"as":[17],"they":[18],"have":[19],"achieved":[20],"great":[21],"success.":[22],"Especially,":[23],"WavLM":[24,62,74,103],"showed":[25],"state-of-the-art":[26],"performance":[27],"on":[28,91],"various":[29],"processing":[31],"tasks.":[32],"To":[33],"better":[34],"understand":[35],"the":[36,85,92,102,105,125,131],"efficacy":[37],"of":[38,54,111],"models":[41],"enhancement,":[44],"this":[46],"work,":[47],"we":[48],"design":[49],"and":[50,63,77,96,115],"conduct":[51],"series":[53],"experiments":[55,90],"with":[56],"three":[57],"resource":[58,128],"conditions":[59],"by":[60],"combining":[61],"two":[64],"high-quality":[65],"enhancement":[67,87,107],"systems.":[68],"Also,":[69],"We":[70],"propose":[71],"regression-based":[73],"training":[75],"objective":[76],"noise-mixing":[79],"data":[80],"configuration":[81],"to":[82],"further":[83],"boost":[84],"downstream":[86],"performance.":[88],"The":[89],"DNS":[93],"challenge":[94],"dataset":[95,99],"simulation":[98],"show":[100],"that":[101],"benefits":[104],"task":[108],"terms":[110],"both":[112],"quality":[114],"recognition":[117],"accuracy,":[118],"especially":[119],"low":[121],"fine-tuning":[122,127],"resources.":[123],"For":[124],"high":[126],"condition,":[129],"only":[130],"word":[132],"error":[133],"rate":[134],"substantially":[136],"improved.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}