{"id":"https://openalex.org/W4400645798","doi":"https://doi.org/10.1109/access.2024.3428364","title":"Unveiling the Linguistic Capabilities of a Self-Supervised Speech Model Through Cross-Lingual Benchmark and Layer- Wise Similarity Analysis","display_name":"Unveiling the Linguistic Capabilities of a Self-Supervised Speech Model Through Cross-Lingual Benchmark and Layer- Wise Similarity Analysis","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400645798","doi":"https://doi.org/10.1109/access.2024.3428364"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3428364","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3428364","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3428364","any_repository_has_fulltext":true},"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/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"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, Yokosuka-shi, Kanagawa-ken, Japan","Tokyo Institute of Technology, Yokohama-shi, Kanagawa-ken, Japan"],"raw_orcid":"https://orcid.org/0009-0003-4322-4127","affiliations":[{"raw_affiliation_string":"NTT Corporation, Yokosuka-shi, Kanagawa-ken, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"Tokyo Institute of Technology, Yokohama-shi, Kanagawa-ken, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"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, Yokosuka-shi, Kanagawa-ken, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5175-7834","affiliations":[{"raw_affiliation_string":"NTT Corporation, Yokosuka-shi, Kanagawa-ken, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046709969","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, Yokosuka-shi, Kanagawa-ken, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Yokosuka-shi, Kanagawa-ken, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071984161","display_name":"Makio Kashino","orcid":"https://orcid.org/0000-0002-4354-6690"},"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":"Makio Kashino","raw_affiliation_strings":["NTT Corporation, Yokosuka-shi, Kanagawa-ken, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4354-6690","affiliations":[{"raw_affiliation_string":"NTT Corporation, Yokosuka-shi, Kanagawa-ken, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.4893,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70689717,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"12","issue":null,"first_page":"98835","last_page":"98855"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9987000226974487,"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":0.8203481435775757},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6548162698745728},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.530693769454956},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5198519825935364},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.4717058837413788},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4524111747741699},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4438523054122925},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4344756007194519},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.42031562328338623},{"id":"https://openalex.org/keywords/paralanguage","display_name":"Paralanguage","score":0.4117681384086609},{"id":"https://openalex.org/keywords/deep-linguistic-processing","display_name":"Deep linguistic processing","score":0.41056448221206665},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36895352602005005},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.30768662691116333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8203481435775757},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6548162698745728},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.530693769454956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5198519825935364},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.4717058837413788},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4524111747741699},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4438523054122925},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4344756007194519},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.42031562328338623},{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.4117681384086609},{"id":"https://openalex.org/C64249296","wikidata":"https://www.wikidata.org/wiki/Q5250411","display_name":"Deep linguistic processing","level":2,"score":0.41056448221206665},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36895352602005005},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.30768662691116333},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3428364","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3428364","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:e4b647188a4c4606a0dc899c95f100cf","is_oa":true,"landing_page_url":"https://doaj.org/article/e4b647188a4c4606a0dc899c95f100cf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 98835-98855 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3428364","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3428364","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":138,"referenced_works":["https://openalex.org/W1635512741","https://openalex.org/W2005522781","https://openalex.org/W2127658298","https://openalex.org/W2130158090","https://openalex.org/W2160815625","https://openalex.org/W2163922914","https://openalex.org/W2739351760","https://openalex.org/W2752796333","https://openalex.org/W2765486990","https://openalex.org/W2783089003","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2913939497","https://openalex.org/W2919115771","https://openalex.org/W2923014074","https://openalex.org/W2962780374","https://openalex.org/W2963242190","https://openalex.org/W2963748441","https://openalex.org/W2963846996","https://openalex.org/W2965373594","https://openalex.org/W2972541922","https://openalex.org/W2978670439","https://openalex.org/W2980282514","https://openalex.org/W2981087920","https://openalex.org/W2998249245","https://openalex.org/W3001279689","https://openalex.org/W3006926732","https://openalex.org/W3011574394","https://openalex.org/W3023371261","https://openalex.org/W3034487470","https://openalex.org/W3035725276","https://openalex.org/W3088409176","https://openalex.org/W3104033643","https://openalex.org/W3104667152","https://openalex.org/W3114651185","https://openalex.org/W3118485687","https://openalex.org/W3129850062","https://openalex.org/W3161695192","https://openalex.org/W3162133897","https://openalex.org/W3174758275","https://openalex.org/W3175898847","https://openalex.org/W3183764363","https://openalex.org/W3195577433","https://openalex.org/W3197259906","https://openalex.org/W3197580070","https://openalex.org/W3197853473","https://openalex.org/W3197956630","https://openalex.org/W3198275944","https://openalex.org/W3198429080","https://openalex.org/W3198771897","https://openalex.org/W3206189675","https://openalex.org/W3207222250","https://openalex.org/W3207558756","https://openalex.org/W3207924272","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W3217767527","https://openalex.org/W4221155340","https://openalex.org/W4224933800","https://openalex.org/W4225096077","https://openalex.org/W4226033575","https://openalex.org/W4226103796","https://openalex.org/W4226380987","https://openalex.org/W4231109964","https://openalex.org/W4253067820","https://openalex.org/W4281492411","https://openalex.org/W4281690148","https://openalex.org/W4285178177","https://openalex.org/W4285250921","https://openalex.org/W4287591426","https://openalex.org/W4291023040","https://openalex.org/W4292825791","https://openalex.org/W4296068815","https://openalex.org/W4297808394","https://openalex.org/W4311137818","https://openalex.org/W4319862410","https://openalex.org/W4323066695","https://openalex.org/W4361994820","https://openalex.org/W4367000428","https://openalex.org/W4372260307","https://openalex.org/W4375869259","https://openalex.org/W4375869301","https://openalex.org/W4378105483","https://openalex.org/W4382246105","https://openalex.org/W4385478010","https://openalex.org/W4385571440","https://openalex.org/W4385822439","https://openalex.org/W4385823298","https://openalex.org/W4385823338","https://openalex.org/W4391021557","https://openalex.org/W4391021682","https://openalex.org/W4391515560","https://openalex.org/W4392019371","https://openalex.org/W4392904752","https://openalex.org/W4392910434","https://openalex.org/W4394671563","https://openalex.org/W4394773771","https://openalex.org/W4401609044","https://openalex.org/W4412284989","https://openalex.org/W6605323724","https://openalex.org/W6635469476","https://openalex.org/W6678992168","https://openalex.org/W6691459498","https://openalex.org/W6745289305","https://openalex.org/W6761472960","https://openalex.org/W6762392948","https://openalex.org/W6763701032","https://openalex.org/W6768817161","https://openalex.org/W6769196770","https://openalex.org/W6771509786","https://openalex.org/W6772230580","https://openalex.org/W6772383348","https://openalex.org/W6779469704","https://openalex.org/W6780218876","https://openalex.org/W6785121581","https://openalex.org/W6786696081","https://openalex.org/W6790356757","https://openalex.org/W6791055906","https://openalex.org/W6795383682","https://openalex.org/W6796464841","https://openalex.org/W6796730497","https://openalex.org/W6800664022","https://openalex.org/W6800751262","https://openalex.org/W6802472062","https://openalex.org/W6803092890","https://openalex.org/W6809947431","https://openalex.org/W6810007534","https://openalex.org/W6810259195","https://openalex.org/W6811170316","https://openalex.org/W6847363464","https://openalex.org/W6850218400","https://openalex.org/W6851949647","https://openalex.org/W6852781825","https://openalex.org/W6852909395","https://openalex.org/W6854228366","https://openalex.org/W6861440175","https://openalex.org/W6862584478"],"related_works":["https://openalex.org/W2064370490","https://openalex.org/W3166813893","https://openalex.org/W2910013580","https://openalex.org/W2391900574","https://openalex.org/W3200958703","https://openalex.org/W1990078780","https://openalex.org/W3108667266","https://openalex.org/W2376619307","https://openalex.org/W3118437876","https://openalex.org/W1530394198"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,6],"(SSL),":[2],"an":[3],"unsupervised":[4],"representation":[5],"technique,":[7],"has":[8],"received":[9],"widespread":[10],"attention":[11],"across":[12],"various":[13],"modalities.":[14],"Speech,":[15],"with":[16,113,150,240],"its":[17,93],"inherent":[18],"complexity":[19],"encompassing":[20],"acoustic":[21],"(e.g.,":[22,30],"speaker,":[23],"phoneme,":[24],"and":[25,28,33,68,92],"paralinguistic":[26],"cues)":[27],"linguistic":[29,47,143,169,175],"words,":[31],"semantics,":[32],"syntax)":[34],"aspects,":[35],"prompts":[36],"a":[37,110,225],"fundamental":[38],"question:":[39],"how":[40],"well":[41],"can":[42,141,210],"speech":[43,51,84,138],"SSL":[44,58,118,139,152,186,208],"models":[45,59,140,187,209,213],"capture":[46],"knowledge":[48],"solely":[49],"from":[50],"data?":[52],"This":[53],"study":[54],"comprehensively":[55],"analyzes":[56],"off-the-shelf":[57],"utilizing":[60],"three":[61],"methods:":[62],"probing":[63,74,107],"tasks,":[64],"layer":[65,128,191],"contribution":[66],"examinations,":[67],"layer-wise":[69],"similarity":[70],"analysis.":[71],"For":[72],"the":[73,83,162,190,236,244],"task,":[75],"to":[76,131,160],"elucidate":[77],"cross-lingual":[78,181],"conditions,":[79],"we":[80,172],"introduce":[81],"SpeechGLUE/SpeechJGLUE,":[82],"version":[85],"of":[86,98,116,246],"General":[87],"Language":[88],"Understanding":[89],"Evaluation":[90],"(GLUE)":[91],"Japanese":[94,212],"variant":[95],"(JGLUE),":[96],"both":[97],"which":[99,127],"comprise":[100],"diverse":[101,203],"natural":[102],"language":[103,220],"understanding":[104],"tasks.":[105,133,164],"The":[106,134],"system":[108],"incorporates":[109],"weighted":[111],"sum":[112],"trainable":[114],"weights":[115],"all":[117],"layers\u2019":[119],"outputs":[120],"into":[121,126],"downstream":[122],"models,":[123],"offering":[124],"insight":[125],"predominantly":[129],"contributes":[130],"addressing":[132],"results":[135],"reveal":[136],"that":[137],"encode":[142],"information,":[144],"albeit":[145],"less":[146],"sophisticated":[147],"information":[148],"than":[149],"text":[151],"models.":[153],"Moreover,":[154],"later":[155],"layers":[156,177,199],"are":[157],"mainly":[158],"utilized":[159],"tackle":[161],"benchmark":[163],"To":[165],"highlight":[166],"their":[167,217],"primary":[168],"encoding":[170,176],"role,":[171],"call":[173],"them":[174],"(LELs).":[178],"However,":[179],"in":[180,196,232],"scenarios,":[182],"e.g.,":[183],"assessing":[184],"English":[185,207,233],"on":[188,202,214],"SpeechJGLUE,":[189,215],"contributions":[192],"equalize,":[193],"suggesting":[194],"challenges":[195],"determining":[197],"suitable":[198],"or":[200],"relying":[201],"cues.":[204],"Nevertheless,":[205],"some":[206],"outperform":[211],"implying":[216],"robustness":[218],"against":[219],"variation.":[221],"Similarity":[222],"analysis":[223],"reveals":[224],"block":[226],"structure":[227,237],"within":[228],"LELs,":[229],"particularly":[230],"evident":[231],"WavLM,":[234],"where":[235],"becomes":[238],"unclear":[239],"non-English/noise":[241],"input,":[242],"reaffirming":[243],"presence":[245],"LELs.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}