{"id":"https://openalex.org/W4401610024","doi":"https://doi.org/10.1109/icasspw62465.2024.10627241","title":"Noise Robust Distillation of Self-Supervised Speech Models via Correlation Metrics","display_name":"Noise Robust Distillation of Self-Supervised Speech Models via Correlation Metrics","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401610024","doi":"https://doi.org/10.1109/icasspw62465.2024.10627241"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10627241","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10627241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5092905575","display_name":"Fabian Ritter-Gutierrez","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Fabian Ritter-Gutierrez","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103339163","display_name":"Kuan-Po Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuan-Po Huang","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104217727","display_name":"Dianwen Ng","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dianwen Ng","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048201022","display_name":"Jeremy H. M. Wong","orcid":"https://orcid.org/0000-0003-3742-7510"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jeremy H.M. Wong","raw_affiliation_strings":["Institute for Infocomm Research (I2R)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R)","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014190404","display_name":"Nancy F. Chen","orcid":"https://orcid.org/0000-0003-0872-5877"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nancy F. Chen","raw_affiliation_strings":["Institute for Infocomm Research (I2R)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R)","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":"33","issue":null,"first_page":"495","last_page":"499"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9828000068664551,"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":0.9828000068664551,"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":0.9071999788284302,"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":0.667823076248169},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6237386465072632},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6189979314804077},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5813775658607483},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5487053394317627},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.48885148763656616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41579994559288025},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3518204689025879},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3508022427558899},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20515510439872742},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1753312647342682}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.667823076248169},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6237386465072632},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6189979314804077},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5813775658607483},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5487053394317627},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.48885148763656616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41579994559288025},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3518204689025879},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3508022427558899},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20515510439872742},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1753312647342682},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10627241","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10627241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1821462560","https://openalex.org/W2289394825","https://openalex.org/W2402040300","https://openalex.org/W3036601975","https://openalex.org/W3197580070","https://openalex.org/W3203140070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4205689591","https://openalex.org/W4224821750","https://openalex.org/W4226380987","https://openalex.org/W4281492411","https://openalex.org/W4283762346","https://openalex.org/W4296068785","https://openalex.org/W4297841280","https://openalex.org/W4319862641","https://openalex.org/W4372260338","https://openalex.org/W4372342491","https://openalex.org/W4375869224","https://openalex.org/W4375869259","https://openalex.org/W6638523607","https://openalex.org/W6780218876","https://openalex.org/W6791742336","https://openalex.org/W6810218740","https://openalex.org/W6838789926","https://openalex.org/W6846807982"],"related_works":["https://openalex.org/W2327107878","https://openalex.org/W1526760723","https://openalex.org/W2171117985","https://openalex.org/W2012356576","https://openalex.org/W2126659863","https://openalex.org/W3112120395","https://openalex.org/W4385670989","https://openalex.org/W2102487628","https://openalex.org/W2009680848","https://openalex.org/W2150465873"],"abstract_inverted_index":{"Compared":[0],"to":[1],"large":[2],"speech":[3],"foundation":[4],"models,":[5],"small":[6],"student":[7,37,46,62],"models":[8],"exhibit":[9],"degraded":[10,39],"noise":[11,21],"robustness.":[12],"The":[13,79],"student\u2019s":[14,76],"robustness":[15,47,71],"can":[16],"be":[17],"improved":[18],"by":[19,57],"introducing":[20],"at":[22],"the":[23,30,59,75,84],"inputs":[24],"during":[25],"pre-training.":[26],"Despite":[27],"this,":[28],"using":[29],"standard":[31],"distillation":[32,49],"loss":[33],"still":[34],"yields":[35],"a":[36],"with":[38,50],"performance.":[40],"Thus,":[41],"this":[42],"paper":[43],"proposes":[44],"improving":[45],"via":[48,74],"correlation":[51],"metrics.":[52],"Teacher":[53],"behavior":[54],"is":[55,72],"learned":[56],"maximizing":[58],"teacher":[60],"and":[61,92],"cross-correlation":[63],"matrix":[64],"between":[65],"their":[66],"representations":[67],"towards":[68],"identity.":[69],"Noise":[70],"encouraged":[73],"self-correlation":[77],"minimization.":[78],"proposed":[80],"method":[81],"consistently":[82],"outperforms":[83],"previous":[85],"approach":[86],"on":[87,97],"Intent":[88],"Classification,":[89],"Keyword":[90],"Spotting,":[91],"Automatic":[93],"Speech":[94],"Recognition":[95],"tasks":[96],"SUPERB":[98],"Challenge.":[99]},"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"}