{"id":"https://openalex.org/W4221140371","doi":"https://doi.org/10.1109/icassp43922.2022.9747379","title":"A Noise-Robust Self-Supervised Pre-Training Model Based Speech Representation Learning for Automatic Speech Recognition","display_name":"A Noise-Robust Self-Supervised Pre-Training Model Based Speech Representation Learning for Automatic Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221140371","doi":"https://doi.org/10.1109/icassp43922.2022.9747379"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747379","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2201.08930","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045966396","display_name":"Qiushi Zhu","orcid":"https://orcid.org/0000-0002-1196-7781"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiu-Shi Zhu","raw_affiliation_strings":["NEL-SLIP, University of Science and Technology of China (USTC),Hefei,China","NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC),Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436848","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0003-1124-0854"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["NEL-SLIP, University of Science and Technology of China (USTC),Hefei,China","State Key Laboratory of Acoustics, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC),Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"State Key Laboratory of Acoustics, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101577318","display_name":"Ziqiang Zhang","orcid":"https://orcid.org/0000-0003-0110-1543"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zi-Qiang Zhang","raw_affiliation_strings":["NEL-SLIP, University of Science and Technology of China (USTC),Hefei,China","NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC),Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101925641","display_name":"Minghui Wu","orcid":"https://orcid.org/0000-0001-8179-7119"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming-Hui Wu","raw_affiliation_strings":["NEL-SLIP, University of Science and Technology of China (USTC),Hefei,China","NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC),Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101716884","display_name":"Xin Fang","orcid":"https://orcid.org/0000-0003-4796-9444"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Fang","raw_affiliation_strings":["NEL-SLIP, University of Science and Technology of China (USTC),Hefei,China","NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC),Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["NEL-SLIP, University of Science and Technology of China (USTC),Hefei,China","NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC),Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5045966396"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":3.2348,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.9335983,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3174","last_page":"3178"},"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":0.9976999759674072,"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":0.9973999857902527,"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/robustness","display_name":"Robustness (evolution)","score":0.8552303314208984},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8189911246299744},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7063906192779541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5603508353233337},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5516383647918701},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5092226266860962},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.49138084053993225},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4778842031955719},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.47478172183036804},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4681921899318695},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4321233034133911},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.22358179092407227}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8552303314208984},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8189911246299744},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7063906192779541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5603508353233337},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5516383647918701},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5092226266860962},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49138084053993225},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4778842031955719},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.47478172183036804},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4681921899318695},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4321233034133911},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.22358179092407227},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747379","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2201.08930","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.08930","pdf_url":"https://arxiv.org/pdf/2201.08930","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:2201.08930","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.08930","pdf_url":"https://arxiv.org/pdf/2201.08930","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4000000059604645}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1882958252","https://openalex.org/W1974387177","https://openalex.org/W2033875152","https://openalex.org/W2064675550","https://openalex.org/W2124509324","https://openalex.org/W2127141656","https://openalex.org/W2193413348","https://openalex.org/W2547875792","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2933138175","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2981991061","https://openalex.org/W2982223350","https://openalex.org/W3003875258","https://openalex.org/W3015213852","https://openalex.org/W3015265920","https://openalex.org/W3016181583","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3097945073","https://openalex.org/W3102342027","https://openalex.org/W3159776099","https://openalex.org/W3163142165","https://openalex.org/W3198771897","https://openalex.org/W4214784181","https://openalex.org/W4297808394","https://openalex.org/W6631190155","https://openalex.org/W6639480849","https://openalex.org/W6687566353","https://openalex.org/W6729448088","https://openalex.org/W6755207826","https://openalex.org/W6769196770","https://openalex.org/W6769238691","https://openalex.org/W6780218876","https://openalex.org/W6792927658"],"related_works":["https://openalex.org/W1999699871","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W2022538999","https://openalex.org/W2021633306","https://openalex.org/W1955763106","https://openalex.org/W2006801911","https://openalex.org/W2002243964","https://openalex.org/W2033669961","https://openalex.org/W3090086172"],"abstract_inverted_index":{"Wav2vec2.0":[0],"is":[1,36,170],"a":[2,25,79,153],"popular":[3],"self-supervised":[4],"pre-training":[5],"framework":[6],"for":[7,123],"learning":[8],"speech":[9,16,103,119],"representations":[10,64],"in":[11,91],"the":[12,29,33,46,68,72,83,101,105,112,117,124,130,137,141,147,158,164,167],"context":[13],"of":[14,49,166,175],"automatic":[15],"recognition":[17],"(ASR).":[18],"It":[19],"was":[20],"shown":[21],"that":[22,55,129],"wav2vec2.0":[23,50,56,98],"has":[24],"good":[26,63],"robustness":[27,35,48],"against":[28],"domain":[30],"shift,":[31],"while":[32],"noise":[34,47,176],"still":[37],"unclear.":[38],"In":[39,162],"this":[40,89,92],"work,":[41],"we":[42,94],"therefore":[43],"first":[44],"analyze":[45],"via":[51],"experiments.":[52],"We":[53],"observe":[54],"pre-trained":[57],"on":[58,71,82,140,157],"noisy":[59,73,102,142],"data":[60],"can":[61,133],"obtain":[62],"and":[65,104],"thus":[66],"improve":[67,136],"ASR":[69,138],"performance":[70,80,139,155],"test":[74,85,143,160],"set,":[75],"which":[76,145],"however":[77],"brings":[78],"degradation":[81],"clean":[84,107,118,159],"set.":[86,161],"To":[87],"avoid":[88],"issue,":[90],"work":[93],"propose":[95],"an":[96],"enhanced":[97],"model.":[99,125],"Specifically,":[100],"corresponding":[106],"version":[108],"are":[109],"fed":[110],"into":[111],"same":[113],"feature":[114],"encoder,":[115],"where":[116],"provides":[120],"training":[121],"targets":[122],"Experimental":[126],"results":[127],"reveal":[128],"proposed":[131,168],"method":[132,169],"not":[134],"only":[135],"set":[144],"surpasses":[146],"original":[148],"wav2vec2.0,":[149],"but":[150],"also":[151],"ensure":[152],"tiny":[154],"decrease":[156],"addition,":[163],"effectiveness":[165],"demonstrated":[171],"under":[172],"different":[173],"types":[174],"conditions.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}