{"id":"https://openalex.org/W4372346788","doi":"https://doi.org/10.1109/icassp49357.2023.10095480","title":"Robustdistiller: Compressing Universal Speech Representations for Enhanced Environment Robustness","display_name":"Robustdistiller: Compressing Universal Speech Representations for Enhanced Environment Robustness","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372346788","doi":"https://doi.org/10.1109/icassp49357.2023.10095480"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095480","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":"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/A5059048857","display_name":"Heitor R. Guimar\u00e3es","orcid":"https://orcid.org/0000-0001-9929-9871"},"institutions":[{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Heitor R. Guimar\u00e3es","raw_affiliation_strings":["Université du Québec,INRS-EMT,Montréal,Canada"],"affiliations":[{"raw_affiliation_string":"Université du Québec,INRS-EMT,Montréal,Canada","institution_ids":["https://openalex.org/I39481719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037046760","display_name":"Arthur Pimentel","orcid":"https://orcid.org/0009-0008-4599-7525"},"institutions":[{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Arthur Pimentel","raw_affiliation_strings":["Université du Québec,INRS-EMT,Montréal,Canada"],"affiliations":[{"raw_affiliation_string":"Université du Québec,INRS-EMT,Montréal,Canada","institution_ids":["https://openalex.org/I39481719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009407218","display_name":"Anderson R. Avila","orcid":"https://orcid.org/0000-0002-3088-5116"},"institutions":[{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Anderson R. Avila","raw_affiliation_strings":["Université du Québec,INRS-EMT,Montréal,Canada"],"affiliations":[{"raw_affiliation_string":"Université du Québec,INRS-EMT,Montréal,Canada","institution_ids":["https://openalex.org/I39481719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028862918","display_name":"Mehdi Rezagholizadeh","orcid":"https://orcid.org/0000-0003-4014-6007"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mehdi Rezagholizadeh","raw_affiliation_strings":["Huawei Noah’s Ark Lab,Montréal,Canada"],"affiliations":[{"raw_affiliation_string":"Huawei Noah’s Ark Lab,Montréal,Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019715118","display_name":"Boxing Chen","orcid":"https://orcid.org/0000-0002-3170-4858"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Boxing Chen","raw_affiliation_strings":["Huawei Noah’s Ark Lab,Montréal,Canada"],"affiliations":[{"raw_affiliation_string":"Huawei Noah’s Ark Lab,Montréal,Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065418889","display_name":"Tiago H. Falk","orcid":"https://orcid.org/0000-0002-5739-2514"},"institutions":[{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tiago H. Falk","raw_affiliation_strings":["Université du Québec,INRS-EMT,Montréal,Canada"],"affiliations":[{"raw_affiliation_string":"Université du Québec,INRS-EMT,Montréal,Canada","institution_ids":["https://openalex.org/I39481719"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5059048857"],"corresponding_institution_ids":["https://openalex.org/I39481719"],"apc_list":null,"apc_paid":null,"fwci":2.1136,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.87871854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"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/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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9995999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7785702347755432},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7109842896461487},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6011852622032166},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5992369055747986},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5273669362068176},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.49982523918151855},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4904486835002899},{"id":"https://openalex.org/keywords/environmental-noise","display_name":"Environmental noise","score":0.4767742455005646},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4660281836986542},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4258812963962555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4016192853450775},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3970988094806671},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11017844080924988},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10443773865699768}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7785702347755432},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7109842896461487},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6011852622032166},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5992369055747986},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5273669362068176},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.49982523918151855},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4904486835002899},{"id":"https://openalex.org/C86781634","wikidata":"https://www.wikidata.org/wiki/Q2478325","display_name":"Environmental noise","level":3,"score":0.4767742455005646},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4660281836986542},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4258812963962555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4016192853450775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3970988094806671},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11017844080924988},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10443773865699768},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095480","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2038484192","https://openalex.org/W2696967604","https://openalex.org/W2995181338","https://openalex.org/W3015191643","https://openalex.org/W3036601975","https://openalex.org/W3163652268","https://openalex.org/W3197580070","https://openalex.org/W3197912330","https://openalex.org/W3198771897","https://openalex.org/W3203140070","https://openalex.org/W3209059054","https://openalex.org/W3209376089","https://openalex.org/W3209984917","https://openalex.org/W4224821750","https://openalex.org/W4225905067","https://openalex.org/W4295723153","https://openalex.org/W4296068785","https://openalex.org/W6752516136","https://openalex.org/W6780218876","https://openalex.org/W6809853447","https://openalex.org/W6810099069","https://openalex.org/W6810856829"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W3000197790","https://openalex.org/W4315865067","https://openalex.org/W2979433843","https://openalex.org/W3208304128"],"abstract_inverted_index":{"Self-supervised":[0],"speech":[1,21],"pre-training":[2],"enables":[3],"deep":[4],"neural":[5],"network":[6],"models":[7],"to":[8,36],"capture":[9],"meaningful":[10],"and":[11,131],"disentangled":[12],"factors":[13],"from":[14],"raw":[15],"waveform":[16],"signals.":[17],"The":[18,88],"learned":[19],"universal":[20,73,100],"representations":[22,74],"can":[23],"then":[24],"be":[25],"used":[26],"across":[27,128],"numerous":[28],"down-stream":[29],"tasks.":[30,108],"These":[31],"representations,":[32,101],"however,":[33],"are":[34],"sensitive":[35],"distribution":[37],"shifts":[38],"caused":[39],"by":[40],"environmental":[41,81],"factors,":[42],"such":[43],"as":[44,102,104,133,135],"noise":[45,129],"and/or":[46],"room":[47],"reverberation.":[48],"Their":[49],"large":[50],"sizes,":[51],"in":[52],"turn,":[53],"make":[54],"them":[55,77],"unfeasible":[56],"for":[57],"edge":[58],"applications.":[59],"In":[60],"this":[61],"work,":[62],"we":[63],"propose":[64],"a":[65,84],"knowledge":[66],"distillation":[67,91],"methodology":[68,114],"termed":[69],"RobustDistiller":[70],"which":[71],"compresses":[72],"while":[75],"making":[76],"more":[78],"robust":[79],"against":[80],"artifacts":[82],"via":[83],"multi-task":[85],"learning":[86],"objective.":[87],"proposed":[89,113],"layer-wise":[90],"recipe":[92],"is":[93],"evaluated":[94],"on":[95,116],"top":[96,117],"of":[97,118,153],"three":[98,106],"well-established":[99],"well":[103,134],"with":[105,142,151],"downstream":[107],"Experimental":[109],"results":[110,141,149],"show":[111],"the":[112,119,139,143,154],"applied":[115],"WavLM":[120],"Base+":[121],"teacher":[122,155],"model":[123,145,156],"outperforming":[124],"all":[125],"other":[126],"benchmarks":[127],"types":[130],"levels,":[132],"reverberation":[136],"times.":[137],"Oftentimes,":[138],"obtained":[140],"student":[144],"(24M":[146],"parameters)":[147],"achieved":[148],"inline":[150],"those":[152],"(95M).":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}