{"id":"https://openalex.org/W4392904968","doi":"https://doi.org/10.1109/icassp48485.2024.10447907","title":"Speech Foundation Models on Intelligibility Prediction for Hearing-Impaired Listeners","display_name":"Speech Foundation Models on Intelligibility Prediction for Hearing-Impaired Listeners","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904968","doi":"https://doi.org/10.1109/icassp48485.2024.10447907"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447907","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04592508v1/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076491406","display_name":"Santiago Cuervo","orcid":null},"institutions":[{"id":"https://openalex.org/I143002897","display_name":"Universit\u00e9 de Toulon","ror":"https://ror.org/02m9kbe37","country_code":"FR","type":"education","lineage":["https://openalex.org/I143002897"]},{"id":"https://openalex.org/I4210114274","display_name":"Laboratoire d\u2019Informatique et Syst\u00e8mes","ror":"https://ror.org/0257sgk90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I143002897","https://openalex.org/I21491767","https://openalex.org/I4210114274"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Santiago Cuervo","raw_affiliation_strings":["Universit&#x00E9; de Toulon, Aix Marseille Univ, CNRS, LIS,France"],"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; de Toulon, Aix Marseille Univ, CNRS, LIS,France","institution_ids":["https://openalex.org/I143002897","https://openalex.org/I4210114274","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013266148","display_name":"Ricard Marxer","orcid":"https://orcid.org/0000-0001-5099-5059"},"institutions":[{"id":"https://openalex.org/I4210114274","display_name":"Laboratoire d\u2019Informatique et Syst\u00e8mes","ror":"https://ror.org/0257sgk90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I143002897","https://openalex.org/I21491767","https://openalex.org/I4210114274"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I143002897","display_name":"Universit\u00e9 de Toulon","ror":"https://ror.org/02m9kbe37","country_code":"FR","type":"education","lineage":["https://openalex.org/I143002897"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ricard Marxer","raw_affiliation_strings":["Universit&#x00E9; de Toulon, Aix Marseille Univ, CNRS, LIS,France"],"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; de Toulon, Aix Marseille Univ, CNRS, LIS,France","institution_ids":["https://openalex.org/I143002897","https://openalex.org/I4210114274","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076491406"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I143002897","https://openalex.org/I4210114274"],"apc_list":null,"apc_paid":null,"fwci":3.3937,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.92954016,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1421","last_page":"1425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.822415828704834},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7058994770050049},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.698699951171875},{"id":"https://openalex.org/keywords/hearing-impaired","display_name":"Hearing impaired","score":0.6133450865745544},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.609038770198822},{"id":"https://openalex.org/keywords/hearing-aid","display_name":"Hearing aid","score":0.5936515927314758},{"id":"https://openalex.org/keywords/speech-perception","display_name":"Speech perception","score":0.5925291180610657},{"id":"https://openalex.org/keywords/clarity","display_name":"CLARITY","score":0.5463682413101196},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15428057312965393},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.153958261013031},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.1324259638786316}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.822415828704834},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7058994770050049},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.698699951171875},{"id":"https://openalex.org/C3020736805","wikidata":"https://www.wikidata.org/wiki/Q16035842","display_name":"Hearing impaired","level":2,"score":0.6133450865745544},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.609038770198822},{"id":"https://openalex.org/C2780801066","wikidata":"https://www.wikidata.org/wiki/Q323808","display_name":"Hearing aid","level":2,"score":0.5936515927314758},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.5925291180610657},{"id":"https://openalex.org/C2777146004","wikidata":"https://www.wikidata.org/wiki/Q14949826","display_name":"CLARITY","level":2,"score":0.5463682413101196},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15428057312965393},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.153958261013031},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.1324259638786316},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447907","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"},{"id":"pmh:oai:HAL:hal-04592508v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04592508","pdf_url":"https://hal.science/hal-04592508v1/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2024, Seoul, South Korea. pp.1421-1425, &#x27E8;10.1109/ICASSP48485.2024.10447907&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04592508v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04592508","pdf_url":"https://hal.science/hal-04592508v1/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2024, Seoul, South Korea. pp.1421-1425, &#x27E8;10.1109/ICASSP48485.2024.10447907&#x27E9;","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2402987151","display_name":null,"funder_award_id":"ANR-20-CE","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G3278450421","display_name":null,"funder_award_id":"ANR-16-CONV-0002","funder_id":"https://openalex.org/F4320309911","funder_display_name":"Aix-Marseille Universit\u00e9"},{"id":"https://openalex.org/G3570594198","display_name":"Microscopic Intelligibility Modeling","funder_award_id":"ANR-20-CE23-0012","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G3969625138","display_name":null,"funder_award_id":"ANR-16-CONV-0002","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G4801681434","display_name":null,"funder_award_id":"ANR-20-CE23-0012-01","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320309911","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392904968.pdf","grobid_xml":"https://content.openalex.org/works/W4392904968.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2092644348","https://openalex.org/W2095705004","https://openalex.org/W2258306745","https://openalex.org/W3036601975","https://openalex.org/W3197580070","https://openalex.org/W3198771897","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4252684946","https://openalex.org/W4287591426","https://openalex.org/W4293363567","https://openalex.org/W4297841451","https://openalex.org/W4320086272","https://openalex.org/W4385245566","https://openalex.org/W4385292550","https://openalex.org/W4385807453","https://openalex.org/W4385822399","https://openalex.org/W4394650347","https://openalex.org/W6674330103","https://openalex.org/W6755207826","https://openalex.org/W6779119091","https://openalex.org/W6780218876","https://openalex.org/W6786696081","https://openalex.org/W6846678071","https://openalex.org/W6847363464","https://openalex.org/W6855359634"],"related_works":["https://openalex.org/W2086338133","https://openalex.org/W4380185653","https://openalex.org/W2325585853","https://openalex.org/W2089150823","https://openalex.org/W4238389554","https://openalex.org/W4206549324","https://openalex.org/W2043356347","https://openalex.org/W2129943590","https://openalex.org/W3124530819","https://openalex.org/W2069303773"],"abstract_inverted_index":{"Speech":[0,52],"foundation":[1],"models":[2],"(SFMs)":[3],"have":[4],"been":[5,24],"benchmarked":[6],"on":[7,48,57,98],"many":[8],"speech":[9,34,131],"processing":[10],"tasks,":[11],"often":[12],"achieving":[13],"state-of-the-art":[14],"performance":[15,114],"with":[16],"minimal":[17],"adaptation.":[18],"However,":[19],"the":[20,33,58,62,69,74,105,121,125],"SFM":[21],"paradigm":[22],"has":[23],"significantly":[25],"less":[26],"explored":[27],"for":[28,130],"applications":[29],"of":[30,45,61,76,100],"interest":[31],"to":[32,72,103],"perception":[35,132],"community.":[36],"In":[37],"this":[38],"paper":[39],"we":[40],"present":[41],"a":[42,88,93],"systematic":[43],"evaluation":[44],"10":[46],"SFMs":[47,102],"one":[49],"such":[50],"application:":[51],"intelligibility":[53],"prediction.":[54],"We":[55,86],"focus":[56],"non-intrusive":[59],"setup":[60],"Clarity":[63],"Prediction":[64],"Challenge":[65],"2":[66],"(CPC2),":[67],"where":[68],"task":[70],"is":[71],"predict":[73],"percentage":[75],"words":[77],"correctly":[78],"perceived":[79],"by":[80],"hearing-impaired":[81],"listeners":[82],"from":[83],"speech-in-noise":[84],"recordings.":[85],"propose":[87],"simple":[89],"method":[90,118],"that":[91],"learns":[92],"lightweight":[94],"specialized":[95],"prediction":[96],"head":[97],"top":[99],"frozen":[101],"approach":[104],"problem.":[106],"Our":[107,117],"results":[108],"reveal":[109],"statistically":[110],"significant":[111],"differences":[112],"in":[113,120,124],"across":[115],"SFMs.":[116],"resulted":[119],"winning":[122],"submission":[123],"CPC2,":[126],"demonstrating":[127],"its":[128],"promise":[129],"applications.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2024-03-19T00:00:00"}
