{"id":"https://openalex.org/W4408355898","doi":"https://doi.org/10.1109/icassp49660.2025.10889651","title":"Towards Automatic Assessment of Self-Supervised Speech Models using Rank","display_name":"Towards Automatic Assessment of Self-Supervised Speech Models using Rank","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355898","doi":"https://doi.org/10.1109/icassp49660.2025.10889651"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5090927958","display_name":"Zakaria Aldeneh","orcid":"https://orcid.org/0000-0003-4599-2448"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zakaria Aldeneh","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059333418","display_name":"Vimal Thilak","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vimal Thilak","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101768343","display_name":"Takuya Higuchi","orcid":"https://orcid.org/0000-0002-0361-7132"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Takuya Higuchi","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112911728","display_name":"Barry-John Theobald","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Barry-John Theobald","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106542588","display_name":"Tatiana Likhomanenko","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tatiana Likhomanenko","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210107260"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9782999753952026,"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":0.9782999753952026,"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":0.9366999864578247,"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":0.7200467586517334},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.6444064974784851},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.524518609046936},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5032545924186707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4816631078720093},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12953469157218933}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7200467586517334},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.6444064974784851},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.524518609046936},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5032545924186707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4816631078720093},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12953469157218933},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":16,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1635512741","https://openalex.org/W2726515241","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4214689175","https://openalex.org/W4281492411","https://openalex.org/W4385822823","https://openalex.org/W4385823192","https://openalex.org/W4393156673","https://openalex.org/W4394862910","https://openalex.org/W6838508485","https://openalex.org/W6845864813","https://openalex.org/W6850812491","https://openalex.org/W6852981819","https://openalex.org/W6859405298"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0],"study":[1],"explores":[2],"using":[3],"embedding":[4,43,122],"rank":[5,44,77,96,123],"as":[6,108],"an":[7],"unsupervised":[8],"evaluation":[9,144],"metric":[10],"for":[11,48,90,104,129],"general-purpose":[12],"speech":[13,65,135],"encoders":[14,26,51],"trained":[15],"via":[16],"self-supervised":[17],"learning":[18],"(SSL).":[19],"Traditionally,":[20],"assessing":[21],"the":[22,34,39,64,68,72,101,118],"performance":[23,81],"of":[24,71],"these":[25],"is":[27],"resource-intensive":[28],"and":[29,89,92],"requires":[30],"labeled":[31,55],"data":[32],"from":[33],"downstream":[35,56,80,87,106],"tasks.":[36],"Inspired":[37],"by":[38],"vision":[40],"domain,":[41,66],"where":[42],"has":[45],"shown":[46],"promise":[47],"evaluating":[49],"image":[50],"without":[52],"tuning":[53],"on":[54],"data,":[57],"this":[58,116],"work":[59],"examines":[60],"its":[61],"applicability":[62],"in":[63,133],"considering":[67],"temporal":[69],"nature":[70],"signals.":[73],"The":[74],"findings":[75],"indicate":[76],"correlates":[78],"with":[79],"within":[82],"encoder":[83],"layers":[84,110],"across":[85],"various":[86],"tasks":[88],"in-":[91],"out-of-domain":[93],"scenarios.":[94],"However,":[95],"does":[97],"not":[98],"reliably":[99],"predict":[100],"best-performing":[102],"layer":[103],"specific":[105],"tasks,":[107],"lower-ranked":[109],"can":[111,124],"outperform":[112],"higher-ranked":[113],"ones.":[114],"Despite":[115],"limitation,":[117],"results":[119],"suggest":[120],"that":[121],"be":[125],"a":[126,138],"valuable":[127],"tool":[128],"monitoring":[130],"training":[131],"progress":[132],"SSL":[134],"models,":[136],"offering":[137],"less":[139],"resource-demanding":[140],"alternative":[141],"to":[142],"traditional":[143],"methods.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}