{"id":"https://openalex.org/W3209984917","doi":"https://doi.org/10.1109/jstsp.2022.3188113","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","display_name":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","publication_year":2022,"publication_date":"2022-07-04","ids":{"openalex":"https://openalex.org/W3209984917","doi":"https://doi.org/10.1109/jstsp.2022.3188113","mag":"3209984917"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2022.3188113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3188113","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/2110.13900","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079533447","display_name":"Sanyuan Chen","orcid":"https://orcid.org/0000-0002-3082-6052"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sanyuan Chen","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101863385","display_name":"Chengyi Wang","orcid":"https://orcid.org/0000-0002-6780-9299"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengyi Wang","raw_affiliation_strings":["Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101416769","display_name":"Zhengyang Chen","orcid":"https://orcid.org/0000-0003-1293-8146"},"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"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhengyang Chen","raw_affiliation_strings":["Microsoft Corp., Redmond, WA, USA","Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp., Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101709477","display_name":"Yu Wu","orcid":null},"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 Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","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 Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345062","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0001-9991-6892"},"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"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft Corp., Redmond, WA, USA","Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp., Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"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":"Jinyu Li","raw_affiliation_strings":["Microsoft Corp., Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp., Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"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":"Naoyuki Kanda","raw_affiliation_strings":["Microsoft Corp., Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp., Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"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 Corp., Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp., Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602536","display_name":"Xiong Xiao","orcid":"https://orcid.org/0009-0001-5128-6518"},"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":"Xiong Xiao","raw_affiliation_strings":["Microsoft Corp., Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp., Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011"},"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":"Jian Wu","raw_affiliation_strings":["Microsoft Corp., Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp., Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106557565","display_name":"Long Zhou","orcid":"https://orcid.org/0009-0006-1919-4943"},"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":"Long Zhou","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010323000","display_name":"Shuo Ren","orcid":null},"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":"Shuo Ren","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"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"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Microsoft Corp., Redmond, WA, USA","Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp., Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342006","display_name":"Yao Qian","orcid":"https://orcid.org/0000-0003-1855-9630"},"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"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yao Qian","raw_affiliation_strings":["Microsoft Corp., Redmond, WA, USA","Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp., Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011"},"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":"Jian Wu","raw_affiliation_strings":["Microsoft Corp., Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp., Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089195158","display_name":"Michael Zeng","orcid":"https://orcid.org/0000-0001-5302-5883"},"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":"Michael Zeng","raw_affiliation_strings":["Microsoft Corp., Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp., Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072540013","display_name":"Xiangzhan Yu","orcid":"https://orcid.org/0000-0002-1183-2844"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangzhan Yu","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014662947","display_name":"Furu Wei","orcid":"https://orcid.org/0000-0002-7810-5852"},"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":"Furu Wei","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":19,"corresponding_author_ids":["https://openalex.org/A5079533447"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":201.2844,"has_fulltext":false,"cited_by_count":1523,"citation_normalized_percentile":{"value":0.99995405,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"16","issue":"6","first_page":"1505","last_page":"1518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.996999979019165,"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/T11309","display_name":"Music and Audio Processing","score":0.9969000220298767,"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":0.8431107997894287},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7364083528518677},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.6232485771179199},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5338445901870728},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4983069896697998},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.48935335874557495},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.484913170337677},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4836072027683258},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4414314925670624},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4220290780067444},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3781950771808624},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.1297595202922821}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8431107997894287},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7364083528518677},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.6232485771179199},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5338445901870728},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4983069896697998},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.48935335874557495},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.484913170337677},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4836072027683258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4414314925670624},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4220290780067444},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3781950771808624},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.1297595202922821},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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":2,"locations":[{"id":"doi:10.1109/jstsp.2022.3188113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3188113","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:2110.13900","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.13900","pdf_url":"https://arxiv.org/pdf/2110.13900","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:2110.13900","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.13900","pdf_url":"https://arxiv.org/pdf/2110.13900","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":133,"referenced_works":["https://openalex.org/W123007118","https://openalex.org/W125553504","https://openalex.org/W1494198834","https://openalex.org/W2030486566","https://openalex.org/W2069681747","https://openalex.org/W2117678320","https://openalex.org/W2127141656","https://openalex.org/W2157161740","https://openalex.org/W2219249508","https://openalex.org/W2331143823","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2758785877","https://openalex.org/W2765425905","https://openalex.org/W2803322398","https://openalex.org/W2808631503","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2936774411","https://openalex.org/W2950813464","https://openalex.org/W2951974815","https://openalex.org/W2953190524","https://openalex.org/W2962850167","https://openalex.org/W2963122170","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963618559","https://openalex.org/W2969985801","https://openalex.org/W2970597249","https://openalex.org/W2972712416","https://openalex.org/W2972943112","https://openalex.org/W2972949456","https://openalex.org/W2973049979","https://openalex.org/W2973157397","https://openalex.org/W2975381464","https://openalex.org/W2979476256","https://openalex.org/W2981087920","https://openalex.org/W2982223350","https://openalex.org/W2991213871","https://openalex.org/W2995181338","https://openalex.org/W2996383576","https://openalex.org/W3002741552","https://openalex.org/W3004728855","https://openalex.org/W3008181812","https://openalex.org/W3015213852","https://openalex.org/W3015265920","https://openalex.org/W3015356564","https://openalex.org/W3016010032","https://openalex.org/W3016011332","https://openalex.org/W3016181583","https://openalex.org/W3016232124","https://openalex.org/W3024869864","https://openalex.org/W3026868282","https://openalex.org/W3033627755","https://openalex.org/W3035202887","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3082274269","https://openalex.org/W3094374485","https://openalex.org/W3095173472","https://openalex.org/W3095189764","https://openalex.org/W3095212884","https://openalex.org/W3095292526","https://openalex.org/W3097286738","https://openalex.org/W3097777922","https://openalex.org/W3099782249","https://openalex.org/W3100270690","https://openalex.org/W3112034174","https://openalex.org/W3119308075","https://openalex.org/W3125596972","https://openalex.org/W3125709657","https://openalex.org/W3139918052","https://openalex.org/W3144173820","https://openalex.org/W3157923770","https://openalex.org/W3160936850","https://openalex.org/W3162648834","https://openalex.org/W3163842642","https://openalex.org/W3165647589","https://openalex.org/W3169320628","https://openalex.org/W3169688220","https://openalex.org/W3174648740","https://openalex.org/W3175898847","https://openalex.org/W3178296206","https://openalex.org/W3178462146","https://openalex.org/W3193846000","https://openalex.org/W3194687854","https://openalex.org/W3196857193","https://openalex.org/W3197042120","https://openalex.org/W3197580070","https://openalex.org/W3198270883","https://openalex.org/W3198694222","https://openalex.org/W3198698812","https://openalex.org/W3198771897","https://openalex.org/W3198858531","https://openalex.org/W3204696009","https://openalex.org/W3205495812","https://openalex.org/W3205644108","https://openalex.org/W3206252155","https://openalex.org/W3206996142","https://openalex.org/W3209059054","https://openalex.org/W3212799896","https://openalex.org/W3212886388","https://openalex.org/W4220731890","https://openalex.org/W4225661121","https://openalex.org/W4226033575","https://openalex.org/W4285250921","https://openalex.org/W4287120025","https://openalex.org/W4287374065","https://openalex.org/W4288089799","https://openalex.org/W4294796045","https://openalex.org/W4297808394","https://openalex.org/W4300427991","https://openalex.org/W4306169301","https://openalex.org/W4307023467","https://openalex.org/W4308349017","https://openalex.org/W4385245566","https://openalex.org/W6688816777","https://openalex.org/W6739901393","https://openalex.org/W6745117592","https://openalex.org/W6757817989","https://openalex.org/W6763701032","https://openalex.org/W6768080748","https://openalex.org/W6769196770","https://openalex.org/W6769627184","https://openalex.org/W6770506093","https://openalex.org/W6779069803","https://openalex.org/W6780218876","https://openalex.org/W6788335241","https://openalex.org/W6791904447","https://openalex.org/W6796242362","https://openalex.org/W6801723603","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2496295964","https://openalex.org/W1546240199","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W1976952689","https://openalex.org/W2336887028","https://openalex.org/W642007152","https://openalex.org/W2154415461","https://openalex.org/W2056066842"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,33],"(SSL)":[2],"achieves":[3,137],"great":[4],"success":[5],"in":[6,67],"speech":[7,17,21,38,57,63,78,85,97,150],"recognition,":[8],"while":[9],"limited":[10],"exploration":[11],"has":[12],"been":[13],"attempted":[14],"for":[15,36,107,148],"other":[16],"processing":[18,151],"tasks.":[19,58],"As":[20],"signal":[22],"contains":[23],"multi-faceted":[24],"information":[25],"including":[26],"speaker":[27],"identity,":[28],"paralinguistics,":[29],"spoken":[30],"content,":[31],"etc.,":[32],"universal":[34],"representations":[35],"all":[37],"tasks":[39,94,152],"is":[40],"challenging.":[41],"To":[42],"tackle":[43],"the":[44,77,83,90,96,108,114,124,141],"problem,":[45],"we":[46],"propose":[47],"a":[48],"new":[49],"pre-trained":[50],"model,":[51],"WavLM,":[52],"to":[53,92,111,131],"solve":[54],"full-stack":[55],"downstream":[56],"WavLM":[59,72,101,135],"jointly":[60],"learns":[61],"masked":[62,84],"prediction":[64],"and":[65,144],"denoising":[66],"pre-training.":[68],"By":[69],"this":[70],"means,":[71],"does":[73],"not":[74],"only":[75],"keep":[76],"content":[79],"modeling":[80],"capability":[81],"by":[82,95],"prediction,":[86],"but":[87],"also":[88,121],"improves":[89],"potential":[91],"non-ASR":[93],"denoising.":[98],"In":[99],"addition,":[100],"employs":[102],"gated":[103],"relative":[104],"position":[105],"bias":[106],"Transformer":[109],"structure":[110],"better":[112],"capture":[113],"sequence":[115],"ordering":[116],"of":[117],"input":[118],"speech.":[119],"We":[120],"scale":[122],"up":[123],"training":[125],"dataset":[126],"from":[127],"60":[128],"k":[129,133],"hours":[130],"94":[132],"hours.":[134],"Large":[136],"state-of-the-art":[138],"performance":[139],"on":[140,153],"SUPERB":[142],"benchmark,":[143],"brings":[145],"significant":[146],"improvements":[147],"various":[149],"their":[154],"representative":[155],"benchmarks.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":73},{"year":2025,"cited_by_count":631},{"year":2024,"cited_by_count":413},{"year":2023,"cited_by_count":323},{"year":2022,"cited_by_count":83}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}