{"id":"https://openalex.org/W4392944340","doi":"https://doi.org/10.1109/iceic61013.2024.10457271","title":"On the Disentanglement and Robustness of Self-Supervised Speech Representations","display_name":"On the Disentanglement and Robustness of Self-Supervised Speech Representations","publication_year":2024,"publication_date":"2024-01-28","ids":{"openalex":"https://openalex.org/W4392944340","doi":"https://doi.org/10.1109/iceic61013.2024.10457271"},"language":"en","primary_location":{"id":"doi:10.1109/iceic61013.2024.10457271","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iceic61013.2024.10457271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/01HSB5QBCX18VRHCVM35PYXTVS/file/01HSB5SJHNAD87JK1YCHC1AVRE.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007667052","display_name":"Yanjue Song","orcid":"https://orcid.org/0000-0002-9684-6611"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Yanjue Song","raw_affiliation_strings":["Ghent University - imec,IDLab,Ghent,Belgium","IDLab, Ghent University - imec, Ghent, Belgium"],"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab,Ghent,Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"IDLab, Ghent University - imec, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100652831","display_name":"Doyeon Kim","orcid":"https://orcid.org/0000-0002-6484-8575"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Doyeon Kim","raw_affiliation_strings":["Yonsei University,Dept. of Electrical and Electronic Eng.,Seoul,Korea","Dept. of Electrical and Electronic Eng., Yonsei University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,Dept. of Electrical and Electronic Eng.,Seoul,Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"Dept. of Electrical and Electronic Eng., Yonsei University, Seoul, Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081844255","display_name":"Nilesh Madhu","orcid":"https://orcid.org/0000-0001-9131-3309"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Nilesh Madhu","raw_affiliation_strings":["Ghent University - imec,IDLab,Ghent,Belgium","IDLab, Ghent University - imec, Ghent, Belgium"],"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab,Ghent,Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"IDLab, Ghent University - imec, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Yonsei University,Dept. of Electrical and Electronic Eng.,Seoul,Korea","Dept. of Electrical and Electronic Eng., Yonsei University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,Dept. of Electrical and Electronic Eng.,Seoul,Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"Dept. of Electrical and Electronic Eng., Yonsei University, Seoul, Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007667052"],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":0.3636,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62226222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"30","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9423999786376953,"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":0.9423999786376953,"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":0.9103000164031982,"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":0.8608739376068115},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6777063012123108},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.529664933681488},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4391515851020813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43213993310928345}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8608739376068115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6777063012123108},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.529664933681488},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4391515851020813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43213993310928345},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iceic61013.2024.10457271","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iceic61013.2024.10457271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:01HSB5QBCX18VRHCVM35PYXTVS","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01HSB5QBCX18VRHCVM35PYXTVS","pdf_url":"https://biblio.ugent.be/publication/01HSB5QBCX18VRHCVM35PYXTVS/file/01HSB5SJHNAD87JK1YCHC1AVRE.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9798350371888","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:01HSB5QBCX18VRHCVM35PYXTVS","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01HSB5QBCX18VRHCVM35PYXTVS","pdf_url":"https://biblio.ugent.be/publication/01HSB5QBCX18VRHCVM35PYXTVS/file/01HSB5SJHNAD87JK1YCHC1AVRE.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9798350371888","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392944340.pdf","grobid_xml":"https://content.openalex.org/works/W4392944340.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2187089797","https://openalex.org/W2555915854","https://openalex.org/W2752796333","https://openalex.org/W2757519008","https://openalex.org/W2963799213","https://openalex.org/W2973157397","https://openalex.org/W2979476256","https://openalex.org/W2982223350","https://openalex.org/W3015213852","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3140429000","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221145109","https://openalex.org/W4224933800","https://openalex.org/W4226033575","https://openalex.org/W4226403810","https://openalex.org/W4281492411","https://openalex.org/W4318351475","https://openalex.org/W4381786045","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6810007534"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0,121],"paper":[1],"conducts":[2],"an":[3],"analysis":[4],"of":[5,12,32,50,73,94,105,110,132],"latent":[6],"embeddings":[7,28],"generated":[8],"by":[9,80,85,100,115],"a":[10,55],"range":[11],"pre-trained,":[13],"self-supervised":[14],"learning":[15],"(SSL)":[16],"models.":[17,134],"Departing":[18],"from":[19],"conventional":[20],"practices":[21],"that":[22,91],"predominantly":[23],"focus":[24],"on":[25],"examining":[26],"these":[27,74],"within":[29],"the":[30,39,48,71,92,101,108,116,128],"realm":[31],"speech":[33],"recognition":[34],"tasks,":[35],"our":[36],"study":[37],"investigates":[38],"characteristics":[40],"associated":[41],"with":[42,58],"speakers":[43],"and":[44,63,103,130],"their":[45],"behavior":[46],"under":[47],"influence":[49],"input":[51],"distortions.":[52],"We":[53,76],"establish":[54],"controlled":[56],"setting":[57],"varying":[59],"background":[60],"noise":[61],"levels":[62],"different":[64],"room":[65],"impulse":[66],"response":[67],"conditions":[68],"to":[69],"assess":[70],"robustness":[72,93],"embeddings.":[75],"measure":[77],"speaker-related":[78],"information":[79,112],"utilizing":[81],"repetitive":[82],"sentences":[83],"spoken":[84],"multiple":[86],"speakers.":[87],"The":[88],"results":[89],"demonstrate":[90],"pre-trained":[95],"SSL":[96,133],"models":[97],"is":[98,113],"influenced":[99],"type":[102],"severity":[104],"distortion,":[106],"whereas":[107],"inclusion":[109],"speaker":[111],"determined":[114],"specific":[117],"pre-training":[118],"approach":[119],"employed.":[120],"distinct":[122],"perspective":[123],"offers":[124],"valuable":[125],"insights":[126],"into":[127],"versatility":[129],"limitations":[131]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}