{"id":"https://openalex.org/W3209376089","doi":"https://doi.org/10.1109/icassp43922.2022.9746220","title":"Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction","display_name":"Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3209376089","doi":"https://doi.org/10.1109/icassp43922.2022.9746220","mag":"3209376089"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746220","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":["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":true,"raw_author_name":"Heming Wang","raw_affiliation_strings":["The Ohio State University,USA","The Ohio State University, USA"],"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/A5100342006","display_name":"Yao Qian","orcid":"https://orcid.org/0000-0003-1855-9630"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Yao Qian","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363470","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0000-0002-7223-1030"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Xiaofei Wang","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377931","display_name":"Yiming Wang","orcid":"https://orcid.org/0000-0002-4215-8055"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Yiming Wang","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"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/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Chengyi Wang","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"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/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"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/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"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/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"last","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"],"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"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101497068"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":2.9156,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.93201133,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6062","last_page":"6066"},"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":0.9983999729156494,"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":0.7713850140571594},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.766995370388031},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.739067792892456},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5927383899688721},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5211584568023682},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5028545260429382},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4970257580280304},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4857092797756195},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4829660952091217},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4341382086277008},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38715213537216187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7713850140571594},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.766995370388031},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.739067792892456},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5927383899688721},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5211584568023682},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5028545260429382},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4970257580280304},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4857092797756195},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4829660952091217},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4341382086277008},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38715213537216187},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746220","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.550000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2024490156","https://openalex.org/W2134800885","https://openalex.org/W2219249508","https://openalex.org/W2636483419","https://openalex.org/W2842511635","https://openalex.org/W2889442120","https://openalex.org/W2962866211","https://openalex.org/W2963399332","https://openalex.org/W2972382840","https://openalex.org/W2972943112","https://openalex.org/W2974321942","https://openalex.org/W2979476256","https://openalex.org/W2982223350","https://openalex.org/W2982471419","https://openalex.org/W2995181338","https://openalex.org/W2998616931","https://openalex.org/W3008912312","https://openalex.org/W3015213852","https://openalex.org/W3024182269","https://openalex.org/W3032514799","https://openalex.org/W3036601975","https://openalex.org/W3093839391","https://openalex.org/W3096408984","https://openalex.org/W3099782249","https://openalex.org/W3100954996","https://openalex.org/W3102342027","https://openalex.org/W3114727685","https://openalex.org/W3140783160","https://openalex.org/W3167207712","https://openalex.org/W3194338569","https://openalex.org/W3196321886","https://openalex.org/W3197411683","https://openalex.org/W4297808394","https://openalex.org/W6679855610","https://openalex.org/W6688816777","https://openalex.org/W6766224279","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6784499681","https://openalex.org/W6787587704","https://openalex.org/W6788335241","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2401089611","https://openalex.org/W4287867034","https://openalex.org/W3108403339","https://openalex.org/W2022538999","https://openalex.org/W2162712524","https://openalex.org/W1955763106","https://openalex.org/W2142924612","https://openalex.org/W2002243964","https://openalex.org/W3090086172","https://openalex.org/W3171883019"],"abstract_inverted_index":{"Noise":[0],"robustness":[1,101],"is":[2,23,92,108],"essential":[3],"for":[4,67,94,130],"deploying":[5],"automatic":[6],"speech":[7,31,38,69,156],"recognition":[8],"(ASR)":[9],"systems":[10],"in":[11],"real-world":[12,154],"environments.":[13],"One":[14],"way":[15],"to":[16,24,39,73,97,149,182],"reduce":[17],"the":[18,36,99,103,115,125,131,153,158,166,169,183],"effect":[19],"of":[20,47,102,117,168,191],"noise":[21,50,100],"interference":[22],"employ":[25,57],"a":[26,52,58,63,75],"preprocessing":[27],"module":[28,77,91],"that":[29],"conducts":[30],"enhancement,":[32],"and":[33,81,106,137],"then":[34],"feed":[35],"enhanced":[37],"an":[40],"ASR":[41,171],"backend.":[42],"In":[43],"this":[44],"work,":[45],"instead":[46],"suppressing":[48],"background":[49],"with":[51,78,188],"conventional":[53],"cascaded":[54],"pipeline,":[55],"we":[56,163,178],"noise-robust":[59],"representation":[60,105],"learned":[61,104],"by":[62],"refined":[64],"self-supervised":[65],"framework":[66],"noisy":[68,87,133,144,155],"recognition.":[70],"We":[71],"propose":[72],"combine":[74],"reconstruction":[76,90],"contrastive":[79],"learning":[80,96],"perform":[82],"multi-task":[83],"continual":[84],"pre-training":[85],"on":[86,143],"data.":[88,193],"The":[89],"used":[93],"auxiliary":[95],"improve":[98],"thus":[107],"not":[109],"required":[110],"during":[111],"inference.":[112],"Experiments":[113],"demonstrate":[114],"effectiveness":[116],"our":[118],"proposed":[119],"method.":[120],"Our":[121],"model":[122],"substantially":[123],"reduces":[124],"word":[126],"error":[127],"rate":[128],"(WER)":[129],"synthesized":[132],"LibriSpeech":[134],"test":[135,146],"sets,":[136],"yields":[138],"around":[139],"4.1/7.5%":[140],"WER":[141],"reduction":[142],"clean/other":[145],"sets":[147],"compared":[148],"data":[150],"augmentation.":[151],"For":[152],"from":[157],"CHiME-4":[159],"challenge":[160],"(1-channel":[161],"track),":[162],"have":[164],"obtained":[165],"state":[167],"art":[170],"performance":[172,181],"without":[173],"any":[174],"denoising":[175],"front-end.":[176],"Moreover,":[177],"achieve":[179],"comparable":[180],"best":[184],"supervised":[185],"approach":[186],"reported":[187],"only":[189],"16%":[190],"labeled":[192]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}