{"id":"https://openalex.org/W4391843427","doi":"https://doi.org/10.3390/info15020114","title":"Understanding Self-Supervised Learning of Speech Representation via Invariance and Redundancy Reduction","display_name":"Understanding Self-Supervised Learning of Speech Representation via Invariance and Redundancy Reduction","publication_year":2024,"publication_date":"2024-02-15","ids":{"openalex":"https://openalex.org/W4391843427","doi":"https://doi.org/10.3390/info15020114"},"language":"en","primary_location":{"id":"doi:10.3390/info15020114","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15020114","pdf_url":"https://www.mdpi.com/2078-2489/15/2/114/pdf?version=1707996593","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/15/2/114/pdf?version=1707996593","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068589144","display_name":"Yusuf Brima","orcid":"https://orcid.org/0000-0002-9975-8676"},"institutions":[{"id":"https://openalex.org/I170658231","display_name":"Osnabr\u00fcck University","ror":"https://ror.org/04qmmjx98","country_code":"DE","type":"education","lineage":["https://openalex.org/I170658231"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Yusuf Brima","raw_affiliation_strings":["Comparative BioCognition, Institute of Cognitive Science, Osnabrueck University, 49074 Osnabr\u00fcck, Germany","Computer Vision, Institute of Cognitive Science, Osnabrueck University, 49074 Osnabr\u00fcck, Germany"],"affiliations":[{"raw_affiliation_string":"Comparative BioCognition, Institute of Cognitive Science, Osnabrueck University, 49074 Osnabr\u00fcck, Germany","institution_ids":["https://openalex.org/I170658231"]},{"raw_affiliation_string":"Computer Vision, Institute of Cognitive Science, Osnabrueck University, 49074 Osnabr\u00fcck, Germany","institution_ids":["https://openalex.org/I170658231"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050933199","display_name":"Ulf Krumnack","orcid":"https://orcid.org/0000-0003-1976-8186"},"institutions":[{"id":"https://openalex.org/I170658231","display_name":"Osnabr\u00fcck University","ror":"https://ror.org/04qmmjx98","country_code":"DE","type":"education","lineage":["https://openalex.org/I170658231"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ulf Krumnack","raw_affiliation_strings":["Computer Vision, Institute of Cognitive Science, Osnabrueck University, 49074 Osnabr\u00fcck, Germany"],"affiliations":[{"raw_affiliation_string":"Computer Vision, Institute of Cognitive Science, Osnabrueck University, 49074 Osnabr\u00fcck, Germany","institution_ids":["https://openalex.org/I170658231"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002820090","display_name":"Simone Pika","orcid":"https://orcid.org/0000-0002-4398-2337"},"institutions":[{"id":"https://openalex.org/I170658231","display_name":"Osnabr\u00fcck University","ror":"https://ror.org/04qmmjx98","country_code":"DE","type":"education","lineage":["https://openalex.org/I170658231"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simone Pika","raw_affiliation_strings":["Comparative BioCognition, Institute of Cognitive Science, Osnabrueck University, 49074 Osnabr\u00fcck, Germany"],"affiliations":[{"raw_affiliation_string":"Comparative BioCognition, Institute of Cognitive Science, Osnabrueck University, 49074 Osnabr\u00fcck, Germany","institution_ids":["https://openalex.org/I170658231"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036545001","display_name":"Gunther Heidemann","orcid":null},"institutions":[{"id":"https://openalex.org/I170658231","display_name":"Osnabr\u00fcck University","ror":"https://ror.org/04qmmjx98","country_code":"DE","type":"education","lineage":["https://openalex.org/I170658231"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gunther Heidemann","raw_affiliation_strings":["Computer Vision, Institute of Cognitive Science, Osnabrueck University, 49074 Osnabr\u00fcck, Germany"],"affiliations":[{"raw_affiliation_string":"Computer Vision, Institute of Cognitive Science, Osnabrueck University, 49074 Osnabr\u00fcck, Germany","institution_ids":["https://openalex.org/I170658231"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068589144"],"corresponding_institution_ids":["https://openalex.org/I170658231"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01261047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"2","first_page":"114","last_page":"114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9315000176429749,"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":0.9315000176429749,"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/redundancy","display_name":"Redundancy (engineering)","score":0.6344209909439087},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.6316491365432739},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4951263964176178},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4688742160797119},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45767447352409363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40312597155570984},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35864147543907166},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3252708315849304},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3244153559207916}],"concepts":[{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6344209909439087},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6316491365432739},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4951263964176178},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4688742160797119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45767447352409363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40312597155570984},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35864147543907166},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3252708315849304},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3244153559207916},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/info15020114","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15020114","pdf_url":"https://www.mdpi.com/2078-2489/15/2/114/pdf?version=1707996593","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:aa7e2b91d7f14583a0a5a05ba9d425e0","is_oa":true,"landing_page_url":"https://doaj.org/article/aa7e2b91d7f14583a0a5a05ba9d425e0","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 15, Iss 2, p 114 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/info15020114","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15020114","pdf_url":"https://www.mdpi.com/2078-2489/15/2/114/pdf?version=1707996593","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2079751820","display_name":null,"funder_award_id":"GRK2340","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G289137143","display_name":null,"funder_award_id":"772000","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5106512922","display_name":null,"funder_award_id":"Deutsche Forschungsgemeinschaft (DFG","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6024419964","display_name":null,"funder_award_id":"Deutsche Forschungsgemeinschaft (DFG)","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6052429835","display_name":null,"funder_award_id":"(DFG)","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G8330397625","display_name":null,"funder_award_id":"Funding","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4391843427.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1975113979","https://openalex.org/W2080794664","https://openalex.org/W2130055919","https://openalex.org/W2500162720","https://openalex.org/W2577680292","https://openalex.org/W2786385136","https://openalex.org/W2787273002","https://openalex.org/W2972943112","https://openalex.org/W2981087920","https://openalex.org/W3005680577","https://openalex.org/W3035060554","https://openalex.org/W3036224891","https://openalex.org/W3036601975","https://openalex.org/W3091905774","https://openalex.org/W3121647842","https://openalex.org/W3134652006","https://openalex.org/W3139022918","https://openalex.org/W3173151551","https://openalex.org/W3209059054","https://openalex.org/W4205742757","https://openalex.org/W4248480789","https://openalex.org/W4281492411","https://openalex.org/W4287812705","https://openalex.org/W4311137818","https://openalex.org/W6723729508","https://openalex.org/W6776700526","https://openalex.org/W6779326418","https://openalex.org/W6779997284","https://openalex.org/W6780218876","https://openalex.org/W6797132756"],"related_works":["https://openalex.org/W1495042958","https://openalex.org/W2494338568","https://openalex.org/W2122678784","https://openalex.org/W2282510344","https://openalex.org/W139987158","https://openalex.org/W2183994405","https://openalex.org/W2062195135","https://openalex.org/W1875646599","https://openalex.org/W2349023125","https://openalex.org/W4253006236"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,10,59,63],"(SSL)":[2],"has":[3],"emerged":[4],"as":[5],"a":[6,159],"promising":[7],"paradigm":[8],"for":[9,104,137,161],"flexible":[11],"speech":[12,71,139],"representations":[13,30,57,77],"from":[14,120],"unlabeled":[15],"data.":[16],"By":[17],"designing":[18],"pretext":[19],"tasks":[20],"that":[21,31],"exploit":[22],"statistical":[23],"regularities,":[24],"SSL":[25,42],"models":[26],"can":[27],"capture":[28],"useful":[29],"are":[32],"transferable":[33],"to":[34,70,170],"downstream":[35,54,80],"tasks.":[36],"Barlow":[37,135],"Twins":[38,136],"(BTs)":[39],"is":[40],"an":[41],"technique":[43],"inspired":[44],"by":[45],"theories":[46],"of":[47,85,106,134],"redundancy":[48,97],"reduction":[49,98],"in":[50,91,144,155],"human":[51],"perception.":[52],"In":[53],"tasks,":[55,81],"BTs":[56,69,174],"accelerate":[58],"and":[60,73,99,112,152,167],"transfer":[61],"this":[62,129,156],"across":[64],"applications.":[65],"This":[66],"study":[67,117],"applies":[68],"data":[72],"evaluates":[74],"the":[75,83,86,124,132,173],"obtained":[76],"on":[78],"several":[79],"showing":[82],"applicability":[84],"approach.":[87],"However,":[88,141],"limitations":[89],"exist":[90],"disentangling":[92],"key":[93],"explanatory":[94],"factors,":[95],"with":[96],"invariance":[100,121],"alone":[101],"being":[102],"insufficient":[103],"factorization":[105],"learned":[107],"latents":[108],"into":[109],"modular,":[110],"compact,":[111],"informative":[113],"codes.":[114],"Our":[115],"ablation":[116],"isolated":[118],"gains":[119,125],"constraints,":[122],"but":[123],"were":[126],"context-dependent.":[127],"Overall,":[128],"work":[130],"substantiates":[131],"potential":[133],"sample-efficient":[138],"encoding.":[140],"challenges":[142],"remain":[143],"achieving":[145],"fully":[146],"hierarchical":[147],"representations.":[148],"The":[149],"analysis":[150],"methodology":[151],"insights":[153],"presented":[154],"paper":[157],"pave":[158],"path":[160],"extensions":[162],"incorporating":[163],"further":[164,171],"inductive":[165],"priors":[166],"perceptual":[168],"principles":[169],"enhance":[172],"self-supervision":[175],"framework.":[176]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}