{"id":"https://openalex.org/W4392904752","doi":"https://doi.org/10.1109/icassp48485.2024.10446422","title":"What Do Self-Supervised Speech and Speaker Models Learn? New Findings from a Cross Model Layer-Wise Analysis","display_name":"What Do Self-Supervised Speech and Speaker Models Learn? New Findings from a Cross Model Layer-Wise Analysis","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904752","doi":"https://doi.org/10.1109/icassp48485.2024.10446422"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5033975068","display_name":"Takanori Ashihara","orcid":"https://orcid.org/0009-0003-4322-4127"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takanori Ashihara","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104231303","display_name":"Kohei Matsuura","orcid":"https://orcid.org/0009-0000-0884-2200"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kohei Matsuura","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112536171","display_name":"Taichi Asami","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taichi Asami","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068604686","display_name":"Yusuke Ijima","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Ijima","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10166","last_page":"10170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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":0.7709395885467529},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.681218147277832},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6223524212837219},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5339428782463074},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5067501664161682},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4481757879257202},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.44557902216911316},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43880656361579895},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4377979338169098}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7709395885467529},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.681218147277832},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6223524212837219},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5339428782463074},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5067501664161682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4481757879257202},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.44557902216911316},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43880656361579895},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4377979338169098},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2972705840","https://openalex.org/W2972943112","https://openalex.org/W2981087920","https://openalex.org/W2991951409","https://openalex.org/W3015648588","https://openalex.org/W3024869864","https://openalex.org/W3034487470","https://openalex.org/W3096017728","https://openalex.org/W3159481202","https://openalex.org/W3161606033","https://openalex.org/W3162133897","https://openalex.org/W3163596720","https://openalex.org/W3197580070","https://openalex.org/W3197853473","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4281492411","https://openalex.org/W4290995108","https://openalex.org/W4296068987","https://openalex.org/W4297808394","https://openalex.org/W4297841416","https://openalex.org/W4297841520","https://openalex.org/W4319862473","https://openalex.org/W4321524405","https://openalex.org/W4372267483","https://openalex.org/W4372340947","https://openalex.org/W4372346385","https://openalex.org/W4375869259","https://openalex.org/W4385478165","https://openalex.org/W4385822952","https://openalex.org/W4385823338","https://openalex.org/W6761472960","https://openalex.org/W6771538394","https://openalex.org/W6780218876","https://openalex.org/W6785121581","https://openalex.org/W6844194202","https://openalex.org/W6849840340"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W3197877226"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,8],"(SSL)":[2],"has":[3,65],"attracted":[4],"increased":[5],"attention":[6],"for":[7,40,51,123],"meaningful":[9],"speech":[10,62,81,101,110,131,171],"representations.":[11,25],"Speech":[12],"SSL":[13,29,73,82,113,172,185],"models,":[14,30,34],"such":[15],"as":[16],"WavLM,":[17],"employ":[18],"masked":[19],"prediction":[20],"training":[21,37],"to":[22,98,109,126,139,156,163,188],"encode":[23],"general-purpose":[24],"In":[26],"contrast,":[27],"speaker":[28,41,72,86,112,165,184,196],"exemplified":[31],"by":[32,103],"DINO-based":[33],"adopt":[35],"utterance-level":[36],"objectives":[38],"primarily":[39],"representation.":[42,197],"Understanding":[43],"how":[44,76,130],"these":[45,91],"models":[46,173,186],"represent":[47,157],"information":[48,71,159,191],"is":[49,132,160],"essential":[50],"refining":[52],"model":[53],"efficiency":[54],"and":[55,75,111,146,182],"effectiveness.":[56],"Unlike":[57],"the":[58,96,141,154],"various":[59,100],"analyses":[60],"of":[61,170],"SSL,":[63],"there":[64],"been":[66],"limited":[67],"investigation":[68],"into":[69],"what":[70],"captures":[74],"its":[77],"representation":[78],"differs":[79],"from":[80],"or":[83],"other":[84],"fully-supervised":[85],"models.":[87,114,148],"This":[88],"paper":[89],"addresses":[90],"fundamental":[92],"questions.":[93],"We":[94,115],"explore":[95],"capacity":[97,155],"capture":[99],"properties":[102],"applying":[104],"SUPERB":[105],"evaluation":[106],"probing":[107],"tasks":[108],"also":[116],"examine":[117],"which":[118],"layers":[119,144,169],"are":[120],"predominantly":[121],"utilized":[122],"each":[124],"task":[125],"identify":[127],"differences":[128],"in":[129,178],"represented.":[133],"Furthermore,":[134],"we":[135],"conduct":[136],"direct":[137],"comparisons":[138],"measure":[140],"similarities":[142],"between":[143],"within":[145],"across":[147],"Our":[149],"analysis":[150],"unveils":[151],"that":[152],"1)":[153],"content":[158],"somewhat":[161],"unrelated":[162],"enhanced":[164],"representation,":[166],"2)":[167],"specific":[168],"would":[174],"be":[175],"partly":[176],"specialized":[177],"capturing":[179],"linguistic":[180,190],"information,":[181],"3)":[183],"tend":[187],"disregard":[189],"but":[192],"exhibit":[193],"more":[194],"sophisticated":[195]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}