{"id":"https://openalex.org/W4388820662","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317139","title":"An Audio-Visual Speech Enhancement System Based on 3D Image Features: An Application in Hearing Aids","display_name":"An Audio-Visual Speech Enhancement System Based on 3D Image Features: An Application in Hearing Aids","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820662","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317139"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317139","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5114101027","display_name":"Yu-Ching Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Ching Chung","raw_affiliation_strings":["National Yang-Ming University,Department of Biomedical Engineering","Department of Biomedical Engineering, National Yang-Ming University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang-Ming University,Department of Biomedical Engineering","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Department of Biomedical Engineering, National Yang-Ming University","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040816118","display_name":"Ji-Yan Han","orcid":"https://orcid.org/0000-0001-9208-8502"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ji-Yan Han","raw_affiliation_strings":["National Yang-Ming University,Department of Biomedical Engineering","Department of Biomedical Engineering, National Yang-Ming University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang-Ming University,Department of Biomedical Engineering","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Department of Biomedical Engineering, National Yang-Ming University","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052406353","display_name":"Bo-Sin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Bo-Sin Wang","raw_affiliation_strings":["National Yang-Ming University,Department of Biomedical Engineering","Department of Biomedical Engineering, National Yang-Ming University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang-Ming University,Department of Biomedical Engineering","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Department of Biomedical Engineering, National Yang-Ming University","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112562051","display_name":"Wei-Zhong Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Zhong Zheng","raw_affiliation_strings":["National Yang-Ming University,Department of Biomedical Engineering","Department of Biomedical Engineering, National Yang-Ming University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang-Ming University,Department of Biomedical Engineering","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Department of Biomedical Engineering, National Yang-Ming University","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108879168","display_name":"Kung-Yao Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kung-Yao Shen","raw_affiliation_strings":["National Yang-Ming University,Department of Biomedical Engineering","Department of Biomedical Engineering, National Yang-Ming University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang-Ming University,Department of Biomedical Engineering","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Department of Biomedical Engineering, National Yang-Ming University","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027128278","display_name":"Ying-Hui Lai","orcid":"https://orcid.org/0000-0003-4120-7289"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ying-Hui Lai","raw_affiliation_strings":["National Yang-Ming University,Department of Biomedical Engineering","Department of Biomedical Engineering, National Yang-Ming University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang-Ming University,Department of Biomedical Engineering","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Department of Biomedical Engineering, National Yang-Ming University","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21106617,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"86","issue":null,"first_page":"1131","last_page":"1137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9997000098228455,"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/T12032","display_name":"Multisensory perception and integration","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6874046325683594},{"id":"https://openalex.org/keywords/hearing-aid","display_name":"Hearing aid","score":0.6820916533470154},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6476069092750549},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.609855055809021},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5099667310714722},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.48520901799201965},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.4294889569282532},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41555649042129517},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32583218812942505},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.290896475315094},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17942184209823608},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.10687321424484253}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6874046325683594},{"id":"https://openalex.org/C2780801066","wikidata":"https://www.wikidata.org/wiki/Q323808","display_name":"Hearing aid","level":2,"score":0.6820916533470154},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6476069092750549},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.609855055809021},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5099667310714722},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.48520901799201965},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.4294889569282532},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41555649042129517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32583218812942505},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.290896475315094},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17942184209823608},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.10687321424484253},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317139","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1789716261","https://openalex.org/W1921093919","https://openalex.org/W1974455017","https://openalex.org/W1993850091","https://openalex.org/W2000005949","https://openalex.org/W2000916836","https://openalex.org/W2015143272","https://openalex.org/W2027222412","https://openalex.org/W2061960534","https://openalex.org/W2067295501","https://openalex.org/W2074426854","https://openalex.org/W2077086984","https://openalex.org/W2081144555","https://openalex.org/W2092644348","https://openalex.org/W2098500213","https://openalex.org/W2106714211","https://openalex.org/W2121973264","https://openalex.org/W2129671742","https://openalex.org/W2141411743","https://openalex.org/W2150251355","https://openalex.org/W2153894152","https://openalex.org/W2158387459","https://openalex.org/W2163368141","https://openalex.org/W2172240374","https://openalex.org/W2591702985","https://openalex.org/W2740570963","https://openalex.org/W2770902190","https://openalex.org/W2788241093","https://openalex.org/W2896325685","https://openalex.org/W2952218014","https://openalex.org/W2962771259","https://openalex.org/W2972592847","https://openalex.org/W3017923487","https://openalex.org/W3099330747","https://openalex.org/W3124666641","https://openalex.org/W3126260881","https://openalex.org/W3136499730","https://openalex.org/W4236965008","https://openalex.org/W4253928870","https://openalex.org/W6763422710","https://openalex.org/W6776614067","https://openalex.org/W6789284391"],"related_works":["https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W4237969969","https://openalex.org/W2085637247","https://openalex.org/W1996635202"],"abstract_inverted_index":{"Previous":[0],"research":[1],"has":[2],"shown":[3],"that":[4,17,40,78],"auditory":[5,43],"and":[6,16,88,100,117,145],"visual":[7,18],"inputs":[8],"are":[9],"not":[10],"asynchronous":[11],"in":[12,23,92,119],"the":[13,24,42,55,64,79,104,135,139,142,148],"human":[14],"brain,":[15],"cues":[19],"can":[20,146],"enhance":[21],"attention":[22],"hearing":[25,106,124,128,152],"process.":[26],"Therefore,":[27],"this":[28],"study":[29],"proposes":[30],"audio-visual":[31],"speech":[32,86,108,130],"enhancement":[33],"(SE)":[34],"with":[35,69,126],"3D":[36,66],"image":[37,67],"features":[38,70],"(AV-3D-SE)":[39],"imitates":[41],"process":[44],"of":[45,82,85,123,141,151],"humans":[46],"to":[47,58,98],"elevate":[48],"listening":[49,149],"quality.":[50],"More":[51],"specifically,":[52],"AV-3D-SE":[53,137],"uses":[54],"FlowNet3D":[56],"model":[57],"predict":[59],"temporal":[60],"facial":[61],"motion":[62],"from":[63],"recorded":[65],"combining":[68],"for":[71],"SE":[72,114,143],"applications.":[73],"The":[74],"evaluation":[75,84],"results":[76],"showed":[77],"average":[80,105],"scores":[81],"perceptual":[83],"quality":[87,109],"short-time":[89],"objective":[90],"intelligibility":[91],"3":[93],"dB":[94],"signal-to-noise":[95],"ratio":[96],"increased":[97],"3.229":[99],"0.914,":[101],"respectively,":[102],"while":[103],"aid":[107,129,153],"index":[110],"significantly":[111],"outperformed":[112],"baseline":[113],"systems":[115],"(audio-only":[116],"audio-visual-2D)":[118],"seven":[120],"typical":[121],"types":[122],"loss":[125],"high":[127],"perception":[131],"index.":[132],"In":[133],"conclusion,":[134],"proposed":[136],"enhances":[138],"effectiveness":[140],"system":[144],"increase":[147],"satisfaction":[150],"users.":[154]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}