{"id":"https://openalex.org/W4372260140","doi":"https://doi.org/10.1109/icassp49357.2023.10095591","title":"DATA2VEC-SG: Improving Self-Supervised Learning Representations for Speech Generation Tasks","display_name":"DATA2VEC-SG: Improving Self-Supervised Learning Representations for Speech Generation Tasks","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260140","doi":"https://doi.org/10.1109/icassp49357.2023.10095591"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095591","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095591","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/A5101497068","display_name":"Heming Wang","orcid":"https://orcid.org/0000-0003-3057-9060"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heming Wang","raw_affiliation_strings":["The Ohio State University,USA","The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053009352","display_name":"Yao Qian","orcid":null},"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":"Yao Qian","raw_affiliation_strings":["Microsoft Corporation,USA","Microsoft Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023001621","display_name":"Hemin Yang","orcid":null},"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":"Hemin Yang","raw_affiliation_strings":["Microsoft Corporation,USA","Microsoft Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071026412","display_name":"Nauyuki Kanda","orcid":null},"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":"Nauyuki Kanda","raw_affiliation_strings":["Microsoft Corporation,USA","Microsoft Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062250845","display_name":"Peidong Wang","orcid":"https://orcid.org/0000-0002-7042-0209"},"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":"Peidong Wang","raw_affiliation_strings":["Microsoft Corporation,USA","Microsoft Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, 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 Corporation,USA","Microsoft Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363489","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0009-0004-6683-3969"},"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":"Xiaofei Wang","raw_affiliation_strings":["Microsoft Corporation,USA","Microsoft Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377935","display_name":"Yiming Wang","orcid":"https://orcid.org/0000-0002-5932-4371"},"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":"Yiming Wang","raw_affiliation_strings":["Microsoft Corporation,USA","Microsoft Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-2599-6752"},"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":"Shujie Liu","raw_affiliation_strings":["Microsoft Corporation,USA","Microsoft Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"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 Corporation,USA","Microsoft Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["The Ohio State University,USA","The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","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 Corporation,USA","Microsoft Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"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":2,"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/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":0.9998000264167786,"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":0.9980999827384949,"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":0.8256148099899292},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6598494052886963},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6153210401535034},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6007891297340393},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4828222692012787},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.47190457582473755},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4657754600048065},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.45687049627304077},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3614620566368103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8256148099899292},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6598494052886963},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6153210401535034},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6007891297340393},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4828222692012787},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.47190457582473755},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4657754600048065},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.45687049627304077},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3614620566368103},{"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},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095591","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095591","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/16","score":0.6399999856948853,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1974387177","https://openalex.org/W2094721231","https://openalex.org/W2134800885","https://openalex.org/W2141998673","https://openalex.org/W2219249508","https://openalex.org/W2460742184","https://openalex.org/W2734774145","https://openalex.org/W2933138175","https://openalex.org/W2972943112","https://openalex.org/W2982223350","https://openalex.org/W2995181338","https://openalex.org/W3015213852","https://openalex.org/W3036601975","https://openalex.org/W3096408984","https://openalex.org/W3097906045","https://openalex.org/W3163464523","https://openalex.org/W3163827866","https://openalex.org/W3206252155","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221145109","https://openalex.org/W4224933800","https://openalex.org/W4226185896","https://openalex.org/W4226403810","https://openalex.org/W4285250921","https://openalex.org/W4296069296","https://openalex.org/W6633117090","https://openalex.org/W6679855610","https://openalex.org/W6688816777","https://openalex.org/W6780218876","https://openalex.org/W6810007534"],"related_works":["https://openalex.org/W2275432853","https://openalex.org/W2559040841","https://openalex.org/W114661351","https://openalex.org/W2184127972","https://openalex.org/W642007152","https://openalex.org/W2131711534","https://openalex.org/W2343205865","https://openalex.org/W2008120082","https://openalex.org/W2810519502","https://openalex.org/W2341426843"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,50],"has":[2],"been":[3],"successfully":[4],"applied":[5],"to":[6,70,82],"various":[7,98],"speech":[8,19,22,26,54,85,99,103,105,132],"recognition":[9,133],"and":[10,21,66,107,138],"understanding":[11],"tasks.":[12,56],"However,":[13],"for":[14],"generative":[15],"tasks":[16,101],"such":[17],"as":[18],"enhancement":[20],"separation,":[23,106],"most":[24],"self-supervised":[25],"representations":[27,69],"did":[28],"not":[29,72],"show":[30],"substantial":[31],"improvements.":[32],"To":[33],"deal":[34],"with":[35],"this":[36,39],"problem,":[37],"in":[38,130,135],"paper,":[40],"we":[41],"propose":[42],"data2vec-SG":[43,58],"(Speech":[44],"Generation),":[45],"which":[46,123],"is":[47,115,124],"a":[48,60],"teacher-student":[49],"framework":[51,93],"that":[52,90],"addresses":[53],"generation":[55,100],"Our":[57],"introduces":[59],"reconstruction":[61],"module":[62],"into":[63],"data2vec":[64],"[1]":[65],"enforces":[67],"the":[68,74,79,91,95,112,127,131],"contain":[71],"only":[73],"semantic":[75],"information":[76],"but":[77],"also":[78,116],"acoustic":[80],"knowledge":[81],"generate":[83],"clean":[84,137],"waveforms.":[86],"Experimental":[87],"results":[88],"demonstrate":[89],"proposed":[92],"boosts":[94],"performance":[96,129],"of":[97,118],"including":[102],"enhancement,":[104],"packet":[108],"loss":[109],"concealment.":[110],"Meanwhile,":[111],"learned":[113],"representation":[114],"capable":[117],"helping":[119],"other":[120],"downstream":[121],"tasks,":[122],"demonstrated":[125],"by":[126],"good":[128],"task":[134],"both":[136],"noisy":[139],"conditions.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}