{"id":"https://openalex.org/W4416249834","doi":"https://doi.org/10.1109/waspaa66052.2025.11230956","title":"Modeling Multi-Level Hearing Loss for Speech Intelligibility Prediction","display_name":"Modeling Multi-Level Hearing Loss for Speech Intelligibility Prediction","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416249834","doi":"https://doi.org/10.1109/waspaa66052.2025.11230956"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230956","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/A5104200268","display_name":"Xiajie Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Xiajie Zhou","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology,Nomi,Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,Nomi,Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005680805","display_name":"Candy Olivia Mawalim","orcid":"https://orcid.org/0000-0001-9853-8893"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Candy Olivia Mawalim","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology,Nomi,Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,Nomi,Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014199725","display_name":"Masashi Unoki","orcid":"https://orcid.org/0000-0002-6605-2052"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Unoki","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology,Nomi,Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,Nomi,Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5104200268"],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36144436,"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":0.9843999743461609,"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":0.9843999743461609,"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":0.007600000128149986,"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/T10334","display_name":"Hearing, Cochlea, Tinnitus, Genetics","score":0.0035000001080334187,"subfield":{"id":"https://openalex.org/subfields/2809","display_name":"Sensory Systems"},"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/interpretability","display_name":"Interpretability","score":0.7211999893188477},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7074999809265137},{"id":"https://openalex.org/keywords/hearing-loss","display_name":"Hearing loss","score":0.5368000268936157},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.47699999809265137},{"id":"https://openalex.org/keywords/speech-perception","display_name":"Speech perception","score":0.46619999408721924},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4142000079154968},{"id":"https://openalex.org/keywords/predictive-modelling","display_name":"Predictive modelling","score":0.34880000352859497},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.3384000062942505},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.33799999952316284}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7211999893188477},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7074999809265137},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6215000152587891},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6018000245094299},{"id":"https://openalex.org/C2780493683","wikidata":"https://www.wikidata.org/wiki/Q16035842","display_name":"Hearing loss","level":2,"score":0.5368000268936157},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.46619999408721924},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C2777443451","wikidata":"https://www.wikidata.org/wiki/Q821413","display_name":"Auditory system","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3050000071525574},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.2973000109195709},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2928999960422516},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28540000319480896},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.2639000117778778},{"id":"https://openalex.org/C119666444","wikidata":"https://www.wikidata.org/wiki/Q5977280","display_name":"Temporal resolution","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230956","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":27,"referenced_works":["https://openalex.org/W1532420390","https://openalex.org/W1970550538","https://openalex.org/W1982822127","https://openalex.org/W1988482942","https://openalex.org/W1993441974","https://openalex.org/W1998302591","https://openalex.org/W2016839233","https://openalex.org/W2023262923","https://openalex.org/W2026207897","https://openalex.org/W2054139811","https://openalex.org/W2054883573","https://openalex.org/W2060514933","https://openalex.org/W2078013908","https://openalex.org/W2084570857","https://openalex.org/W2562823519","https://openalex.org/W2735705865","https://openalex.org/W2949676527","https://openalex.org/W3032727804","https://openalex.org/W3106864934","https://openalex.org/W3111065375","https://openalex.org/W3197419241","https://openalex.org/W3200289341","https://openalex.org/W3203798222","https://openalex.org/W4220971750","https://openalex.org/W4295530652","https://openalex.org/W4392903483","https://openalex.org/W4409063389"],"related_works":[],"abstract_inverted_index":{"The":[0],"diverse":[1],"perceptual":[2],"consequences":[3],"of":[4,100,169,188],"hearing":[5,50,158],"loss":[6,51,81,159],"severely":[7],"impede":[8],"speech":[9,39,102,104,129,199],"communication,":[10],"but":[11],"standard":[12],"clinical":[13],"audiometry,":[14],"which":[15,76],"is":[16],"focused":[17],"on":[18,133],"threshold-based":[19],"frequency":[20,28,192],"sensitivity,":[21],"does":[22],"not":[23],"adequately":[24],"capture":[25],"deficits":[26],"in":[27,105,153,205],"and":[29,57,103,124,156,175,193,202],"temporal":[30,63,194],"resolution.":[31],"To":[32],"address":[33],"this":[34],"limitation,":[35],"we":[36],"propose":[37],"a":[38,114,162,176],"intelligibility":[40,130,200],"prediction":[41,201],"method":[42,143],"that":[43,119,140],"explicitly":[44,189],"simulates":[45],"auditory":[46,79,206],"degradations":[47,196],"according":[48],"to":[49,62,112,127,197],"severity":[52],"by":[53],"broadening":[54],"cochlear":[55],"filters":[56],"applying":[58],"low-pass":[59],"modulation":[60,73,85],"filtering":[61],"envelopes.":[64],"Speech":[65,147],"signals":[66],"are":[67,110],"subsequently":[68],"analyzed":[69],"using":[70],"the":[71,83,94,97,121,134,141,145,172,180,186],"spectro-temporal":[72],"(STM)":[74],"representations,":[75],"reflect":[77],"how":[78],"resolution":[80,195],"alters":[82],"underlying":[84],"structure.":[86],"In":[87],"addition,":[88],"normalized":[89],"cross-correlation":[90],"(NCC)":[91],"matrices":[92],"quantify":[93],"similarity":[95],"between":[96],"STM":[98,122],"representations":[99],"clean":[101],"noise.":[106],"These":[107,183],"auditory-informed":[108],"features":[109],"utilized":[111],"train":[113],"Vision":[115],"Transformer-based":[116],"regression":[117],"model":[118],"integrates":[120],"maps":[123],"NCC":[125],"embeddings":[126],"estimate":[128],"scores.":[131],"Evaluations":[132],"Clarity":[135],"Prediction":[136],"Challenge":[137],"corpus":[138],"show":[139],"proposed":[142],"outperforms":[144],"Hearing-Aid":[146],"Perception":[148],"Index":[149],"v2":[150],"(HASPI":[151],"v2)":[152],"both":[154],"mild":[155,173],"moderate-to-severe":[157,181],"groups,":[160],"with":[161],"relative":[163],"root":[164],"mean":[165],"squared":[166],"error":[167],"reduction":[168,178],"16.5%":[170],"for":[171,179],"group":[174],"6.1%":[177],"group.":[182],"results":[184],"highlight":[185],"importance":[187],"modeling":[190],"listener-specific":[191],"improve":[198],"provide":[203],"interpretability":[204],"distortions.":[207]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}