{"id":"https://openalex.org/W4416251920","doi":"https://doi.org/10.1109/waspaa66052.2025.11230944","title":"Unveiling the Best Practices for Applying Speech Foundation Models to Speech Intelligibility Prediction for Hearing-Impaired People","display_name":"Unveiling the Best Practices for Applying Speech Foundation Models to Speech Intelligibility Prediction for Hearing-Impaired People","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416251920","doi":"https://doi.org/10.1109/waspaa66052.2025.11230944"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230944","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"article","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/A5018174793","display_name":"Haoshuai Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I81672605","display_name":"Orion Corporation (United Kingdom)","ror":"https://ror.org/01ny43313","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210118237","https://openalex.org/I81672605"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Haoshuai Zhou","raw_affiliation_strings":["Orka Labs Inc.,China"],"affiliations":[{"raw_affiliation_string":"Orka Labs Inc.,China","institution_ids":["https://openalex.org/I81672605"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119835693","display_name":"Boxuan Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I81672605","display_name":"Orion Corporation (United Kingdom)","ror":"https://ror.org/01ny43313","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210118237","https://openalex.org/I81672605"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Boxuan Cao","raw_affiliation_strings":["Orka Labs Inc.,China"],"affiliations":[{"raw_affiliation_string":"Orka Labs Inc.,China","institution_ids":["https://openalex.org/I81672605"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119835694","display_name":"Changgeng Mo","orcid":null},"institutions":[{"id":"https://openalex.org/I81672605","display_name":"Orion Corporation (United Kingdom)","ror":"https://ror.org/01ny43313","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210118237","https://openalex.org/I81672605"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Changgeng Mo","raw_affiliation_strings":["Orka Labs Inc.,China"],"affiliations":[{"raw_affiliation_string":"Orka Labs Inc.,China","institution_ids":["https://openalex.org/I81672605"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101399443","display_name":"Linkai Li","orcid":"https://orcid.org/0009-0001-1675-1672"},"institutions":[{"id":"https://openalex.org/I81672605","display_name":"Orion Corporation (United Kingdom)","ror":"https://ror.org/01ny43313","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210118237","https://openalex.org/I81672605"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Linkai Li","raw_affiliation_strings":["Orka Labs Inc.,China"],"affiliations":[{"raw_affiliation_string":"Orka Labs Inc.,China","institution_ids":["https://openalex.org/I81672605"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008249217","display_name":"Shan Xiang Wang","orcid":"https://orcid.org/0009-0001-3733-0455"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shan Xiang Wang","raw_affiliation_strings":["Stanford University,Electrical Engineering,United States"],"affiliations":[{"raw_affiliation_string":"Stanford University,Electrical Engineering,United States","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018174793"],"corresponding_institution_ids":["https://openalex.org/I81672605"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36215267,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.8925999999046326,"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"}},"topics":[{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.8925999999046326,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.0649000033736229,"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/T10863","display_name":"Voice and Speech Disorders","score":0.007300000172108412,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7775999903678894},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5309000015258789},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4871000051498413},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4860999882221222},{"id":"https://openalex.org/keywords/best-practice","display_name":"Best practice","score":0.4812999963760376}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7775999903678894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6028000116348267},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5309000015258789},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4871000051498413},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4860999882221222},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.4812999963760376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45419999957084656},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38119998574256897},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3553999960422516},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2653000056743622},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230944","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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":17,"referenced_works":["https://openalex.org/W2092644348","https://openalex.org/W2599571402","https://openalex.org/W3180983510","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W4220971750","https://openalex.org/W4297841316","https://openalex.org/W4319862255","https://openalex.org/W4385807453","https://openalex.org/W4386764924","https://openalex.org/W4391021542","https://openalex.org/W4391021675","https://openalex.org/W4392903483","https://openalex.org/W4392903985","https://openalex.org/W4392904968","https://openalex.org/W4402111558","https://openalex.org/W4402112192"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"foundation":[1],"models":[2,99],"(SFMs)":[3],"have":[4],"demonstrated":[5],"strong":[6],"performance":[7,46],"across":[8],"a":[9,36,71],"variety":[10],"of":[11],"downstream":[12],"tasks,":[13],"including":[14],"speech":[15,128],"intelligibility":[16,129],"prediction":[17,55,85,130],"for":[18,25,83,127,131],"hearing-impaired":[19,132],"people":[20],"(SIP-HI).":[21],"However,":[22],"optimizing":[23],"SFMs":[24,93,126],"SIP-HI":[26,45,116],"has":[27],"been":[28],"insufficiently":[29],"explored.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34,104],"conduct":[35],"comprehensive":[37],"study":[38,119],"to":[39,66],"identify":[40],"key":[41,109],"design":[42],"factors":[43],"affecting":[44],"with":[47,96],"5":[48],"SFMs,":[49],"focusing":[50],"on":[51,115],"encoder":[52,73],"layer":[53,74],"selection,":[54],"head":[56],"architecture,":[57],"and":[58,112],"ensemble":[59],"configurations.":[60],"Our":[61,118],"findings":[62],"show":[63],"that,":[64],"contrary":[65],"traditional":[67],"use-all-layers":[68],"methods,":[69],"selecting":[70],"single":[72],"yields":[75],"better":[76],"results.":[77],"Additionally,":[78],"temporal":[79],"modeling":[80],"is":[81],"crucial":[82],"effective":[84],"heads.":[86],"We":[87],"also":[88],"demonstrate":[89],"that":[90],"ensembling":[91],"multiple":[92],"improves":[94],"performance,":[95],"stronger":[97],"individual":[98],"providing":[100],"greater":[101],"benefit.":[102],"Finally,":[103],"explore":[105],"the":[106],"relationship":[107],"between":[108],"SFM":[110],"attributes":[111],"their":[113],"impact":[114],"performance.":[117],"offers":[120],"practical":[121],"insights":[122],"into":[123],"effectively":[124],"adapting":[125],"populations.":[133]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}
