{"id":"https://openalex.org/W4385485012","doi":"https://doi.org/10.1109/icasspw59220.2023.10193370","title":"A Vision-Assisted Hearing Aid System Based on Deep Learning","display_name":"A Vision-Assisted Hearing Aid System Based on Deep Learning","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4385485012","doi":"https://doi.org/10.1109/icasspw59220.2023.10193370"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw59220.2023.10193370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5063187524","display_name":"Daniel Michelsanti","orcid":"https://orcid.org/0000-0002-3575-1600"},"institutions":[{"id":"https://openalex.org/I4210130492","display_name":"Oticon Medical (Denmark)","ror":"https://ror.org/03c5ds320","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210130492"]},{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Daniel Michelsanti","raw_affiliation_strings":["Oticon A/S,Denmark","Oticon A/S, Denmark","Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oticon A/S,Denmark","institution_ids":["https://openalex.org/I4210130492"]},{"raw_affiliation_string":"Oticon A/S, Denmark","institution_ids":["https://openalex.org/I4210130492"]},{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[{"id":"https://openalex.org/I4210130492","display_name":"Oticon Medical (Denmark)","ror":"https://ror.org/03c5ds320","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210130492"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["Oticon A/S,Denmark","Oticon A/S, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oticon A/S,Denmark","institution_ids":["https://openalex.org/I4210130492"]},{"raw_affiliation_string":"Oticon A/S, Denmark","institution_ids":["https://openalex.org/I4210130492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077921236","display_name":"Sergi Rotger-Griful","orcid":"https://orcid.org/0000-0002-9002-4780"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sergi Rotger-Griful","raw_affiliation_strings":["Eriksholm Research Centre,Denmark","Eriksholm Research Centre, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eriksholm Research Centre,Denmark","institution_ids":[]},{"raw_affiliation_string":"Eriksholm Research Centre, Denmark","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101679595","display_name":"Jesper Jensen","orcid":"https://orcid.org/0000-0003-1478-622X"},"institutions":[{"id":"https://openalex.org/I4210130492","display_name":"Oticon Medical (Denmark)","ror":"https://ror.org/03c5ds320","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210130492"]},{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jesper Jensen","raw_affiliation_strings":["Oticon A/S,Denmark","Oticon A/S, Denmark","Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oticon A/S,Denmark","institution_ids":["https://openalex.org/I4210130492"]},{"raw_affiliation_string":"Oticon A/S, Denmark","institution_ids":["https://openalex.org/I4210130492"]},{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9988999962806702,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.7500689029693604},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7464849352836609},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6116766929626465},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6075533628463745},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.6014664769172668},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5693525671958923},{"id":"https://openalex.org/keywords/hearing-aid","display_name":"Hearing aid","score":0.5066519379615784},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.442584753036499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4416344463825226},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4177991449832916},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3637259006500244},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2878108322620392},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08810845017433167},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06690913438796997}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7500689029693604},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7464849352836609},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6116766929626465},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6075533628463745},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.6014664769172668},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5693525671958923},{"id":"https://openalex.org/C2780801066","wikidata":"https://www.wikidata.org/wiki/Q323808","display_name":"Hearing aid","level":2,"score":0.5066519379615784},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.442584753036499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4416344463825226},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4177991449832916},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3637259006500244},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2878108322620392},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08810845017433167},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06690913438796997},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icasspw59220.2023.10193370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/68d87122-d03c-4c89-ae30-7419e913d82a","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/68d87122-d03c-4c89-ae30-7419e913d82a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Michelsanti, D, Tan, Z H, Rotger-Griful, S & Jensen, J 2023, A Vision-Assisted Hearing Aid System Based on Deep Learning. in ICASSPW 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, Proceedings., 10193370, IEEE (Institute of Electrical and Electronics Engineers), 2023 IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, ICASSPW 2023, Rhodes Island, Greece, 04/06/2023. https://doi.org/10.1109/ICASSPW59220.2023.10193370","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.550000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2009649672","https://openalex.org/W2015143272","https://openalex.org/W2168729028","https://openalex.org/W2516001803","https://openalex.org/W2517616541","https://openalex.org/W2900292050","https://openalex.org/W2901702433","https://openalex.org/W2962866211","https://openalex.org/W2963082324","https://openalex.org/W2964171275","https://openalex.org/W3136499730","https://openalex.org/W3160348851","https://openalex.org/W3162341667","https://openalex.org/W3167533889","https://openalex.org/W4253928870","https://openalex.org/W4289665794","https://openalex.org/W4295312788","https://openalex.org/W6631190155","https://openalex.org/W6766978945"],"related_works":["https://openalex.org/W2438174805","https://openalex.org/W2072343332","https://openalex.org/W2033836157","https://openalex.org/W1879255185","https://openalex.org/W4254938824","https://openalex.org/W1998727140","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2380771148"],"abstract_inverted_index":{"Audio-visual":[0],"speech":[1,16,37],"enhancement":[2],"(SE)":[3],"is":[4],"the":[5,9,69,76,79,85,106],"task":[6],"of":[7,75],"reducing":[8],"acoustic":[10,20,40,90],"background":[11],"noise":[12,80,125],"in":[13,42],"a":[14,36,50,56,94,102],"degraded":[15],"signal":[17,38,123],"using":[18,39],"both":[19],"and":[21,78],"visual":[22,32],"information.":[23],"In":[24],"this":[25,65],"work,":[26],"we":[27,47,63,83,109],"study":[28],"how":[29],"to":[30,34,54,67,88,124],"incorporate":[31],"information":[33],"enhance":[35],"beamformers":[41],"hearing":[43],"aids":[44],"(HAs).":[45],"Specifically,":[46],"first":[48],"trained":[49],"deep":[51],"learning":[52],"model":[53],"estimate":[55,68],"time-frequency":[57],"mask":[58,66],"from":[59],"audio-visual":[60],"data.":[61],"Then,":[62],"apply":[64],"inter-microphone":[70],"power":[71],"spectral":[72],"densities":[73],"(PSDs)":[74],"clean":[77],"signal.":[81],"Finally,":[82],"used":[84],"estimated":[86],"PSDs":[87],"build":[89],"beamformers.":[91],"Assuming":[92],"that":[93,111],"HA":[95,118],"user":[96],"wears":[97],"an":[98],"add-on":[99],"device":[100],"comprising":[101],"camera":[103],"pointing":[104],"at":[105,121],"target":[107],"speaker,":[108],"show":[110],"our":[112],"method":[113],"can":[114],"be":[115],"beneficial":[116],"for":[117],"systems":[119],"especially":[120],"low":[122],"ratios":[126],"(SNRs).":[127]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}