{"id":"https://openalex.org/W4416750535","doi":"https://doi.org/10.1109/sips66314.2025.11261312","title":"AECRN: A Unified Neural-Network for Improving Hearing Aid Speech Enhancement","display_name":"AECRN: A Unified Neural-Network for Improving Hearing Aid Speech Enhancement","publication_year":2025,"publication_date":"2025-11-01","ids":{"openalex":"https://openalex.org/W4416750535","doi":"https://doi.org/10.1109/sips66314.2025.11261312"},"language":null,"primary_location":{"id":"doi:10.1109/sips66314.2025.11261312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sips66314.2025.11261312","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 Signal Processing Systems (SiPS)","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/A5119835693","display_name":"Boxuan Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091156","display_name":"SAIC-GM (China)","ror":"https://ror.org/00h64t852","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091156"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Boxuan Cao","raw_affiliation_strings":["Orka Labs Inc.,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Orka Labs Inc.,Shanghai,China","institution_ids":["https://openalex.org/I4210091156"]}]},{"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/I1743320","display_name":"Palo Alto University","ror":"https://ror.org/04f812k67","country_code":"US","type":"education","lineage":["https://openalex.org/I1743320"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linkai Li","raw_affiliation_strings":["Electrical Engineering Stanford University,Palo Alto,United States"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering Stanford University,Palo Alto,United States","institution_ids":["https://openalex.org/I1743320"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119835694","display_name":"Changgeng Mo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091156","display_name":"SAIC-GM (China)","ror":"https://ror.org/00h64t852","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091156"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changgeng Mo","raw_affiliation_strings":["Orka Labs Inc.,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Orka Labs Inc.,Shanghai,China","institution_ids":["https://openalex.org/I4210091156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018174793","display_name":"Haoshuai Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091156","display_name":"SAIC-GM (China)","ror":"https://ror.org/00h64t852","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091156"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoshuai Zhou","raw_affiliation_strings":["Orka Labs Inc.,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Orka Labs Inc.,Shanghai,China","institution_ids":["https://openalex.org/I4210091156"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035138091","display_name":"Shan X. Wang","orcid":"https://orcid.org/0000-0001-8420-9554"},"institutions":[{"id":"https://openalex.org/I1743320","display_name":"Palo Alto University","ror":"https://ror.org/04f812k67","country_code":"US","type":"education","lineage":["https://openalex.org/I1743320"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shan Xiang Wang","raw_affiliation_strings":["Electrical Engineering Stanford University,Palo Alto,United States"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering Stanford University,Palo Alto,United States","institution_ids":["https://openalex.org/I1743320"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5119835693"],"corresponding_institution_ids":["https://openalex.org/I4210091156"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38796169,"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":0.6319000124931335,"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":0.6319000124931335,"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":0.3538999855518341,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.003100000089034438,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7113000154495239},{"id":"https://openalex.org/keywords/hearing-aid","display_name":"Hearing aid","score":0.6155999898910522},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.569100022315979},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5088000297546387},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.43560001254081726},{"id":"https://openalex.org/keywords/audiogram","display_name":"Audiogram","score":0.4226999878883362},{"id":"https://openalex.org/keywords/speech-perception","display_name":"Speech perception","score":0.39430001378059387},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.3716000020503998}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7113000154495239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6942999958992004},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.65829998254776},{"id":"https://openalex.org/C2780801066","wikidata":"https://www.wikidata.org/wiki/Q323808","display_name":"Hearing aid","level":2,"score":0.6155999898910522},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.569100022315979},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5088000297546387},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.43560001254081726},{"id":"https://openalex.org/C17743292","wikidata":"https://www.wikidata.org/wiki/Q781050","display_name":"Audiogram","level":3,"score":0.4226999878883362},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.39430001378059387},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.36739999055862427},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C87133666","wikidata":"https://www.wikidata.org/wiki/Q1161699","display_name":"Dynamic range","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.32919999957084656},{"id":"https://openalex.org/C2780493683","wikidata":"https://www.wikidata.org/wiki/Q16035842","display_name":"Hearing loss","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C150178126","wikidata":"https://www.wikidata.org/wiki/Q18433212","display_name":"Dynamic range compression","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2906000018119812},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2612000107765198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sips66314.2025.11261312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sips66314.2025.11261312","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 Signal Processing Systems (SiPS)","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":31,"referenced_works":["https://openalex.org/W201745378","https://openalex.org/W1501967649","https://openalex.org/W1552314771","https://openalex.org/W1582976041","https://openalex.org/W1968168351","https://openalex.org/W1988482942","https://openalex.org/W1995117235","https://openalex.org/W2036441505","https://openalex.org/W2048708674","https://openalex.org/W2051428568","https://openalex.org/W2067295501","https://openalex.org/W2094721231","https://openalex.org/W2104058659","https://openalex.org/W2124928620","https://openalex.org/W2168548156","https://openalex.org/W2780646907","https://openalex.org/W2889442120","https://openalex.org/W2891433113","https://openalex.org/W2895953958","https://openalex.org/W2936689732","https://openalex.org/W2963868408","https://openalex.org/W3032727804","https://openalex.org/W3082484524","https://openalex.org/W3198740661","https://openalex.org/W4225335671","https://openalex.org/W4283382066","https://openalex.org/W4285295538","https://openalex.org/W4321002349","https://openalex.org/W4379033920","https://openalex.org/W4386765101","https://openalex.org/W4388095751"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"hearing":[1,88,187],"aids":[2],"typically":[3],"adopt":[4],"a":[5,76,92],"cascaded":[6,148,169],"architecture":[7],"where":[8],"noise":[9,48,53,85],"reduction":[10],"(NR)":[11],"and":[12,63,87,161],"wide":[13],"dynamic":[14],"range":[15],"compression":[16],"(WDRC)":[17],"operate":[18],"as":[19,120],"separate,":[20],"independently":[21],"optimized":[22],"modules.":[23],"The":[24,125],"conventional":[25,147],"approach":[26],"first":[27],"applies":[28],"NR":[29],"models":[30],"designed":[31],"for":[32,39,186],"normal":[33],"hearing,":[34],"followed":[35],"by":[36],"WDRC":[37,57],"tuned":[38],"clean":[40,115],"speech,":[41,116],"which":[42],"leads":[43],"to":[44,107,113,133,168,180],"inherent":[45],"limitations.":[46],"Imperfect":[47],"suppression":[49,86],"results":[50,139],"in":[51,154,191],"residual":[52],"that":[54,82,141],"degrades":[55],"subsequent":[56],"performance,":[58],"ultimately":[59],"compromising":[60],"amplification":[61],"quality":[62],"overall":[64],"effectiveness,":[65],"especially":[66],"under":[67],"challenging":[68,192],"acoustic":[69,193],"conditions.":[70],"To":[71],"address":[72],"this,":[73],"we":[74],"propose":[75],"novel":[77],"end-toend":[78],"speech":[79,112],"enhancement":[80],"model":[81,179],"jointly":[83],"optimizes":[84],"loss":[89],"compensation":[90],"within":[91],"unified":[93],"framework.":[94],"Our":[95],"architecture,":[96],"the":[97,104,142,174,183],"Audiogram-Embedded":[98],"Convolutional":[99],"Recurrent":[100],"Network":[101],"(AECRN),":[102],"extends":[103],"CRN":[105],"framework":[106],"directly":[108],"map":[109],"noisy":[110],"input":[111,123],"compensated":[114],"incorporating":[117],"audiogram":[118],"data":[119],"an":[121],"additional":[122],"feature.":[124],"system":[126],"is":[127],"trained":[128],"using":[129],"NAL-NL2":[130],"prescription":[131],"targets":[132],"ensure":[134],"clinically":[135],"valid":[136],"amplification.":[137],"Experimental":[138],"demonstrate":[140],"proposed":[143],"AECRN":[144],"significantly":[145,181],"outperforms":[146],"systems,":[149],"achieving":[150],"$50-60":[151],"\\%$":[152],"improvements":[153],"both":[155],"Hearing-Aid":[156,162],"Speech":[157,163],"Perception":[158],"Index":[159,165],"(HASPI)":[160],"Quality":[164],"(HASQI)":[166],"compared":[167],"systems.":[170],"These":[171],"advances":[172],"underscore":[173],"potential":[175],"of":[176],"our":[177],"single-stage":[178],"enhance":[182],"listening":[184],"experience":[185],"aid":[188],"users,":[189],"particularly":[190],"environments.":[194]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}