{"id":"https://openalex.org/W4385478292","doi":"https://doi.org/10.1109/icasspw59220.2023.10192961","title":"Towards Pose-Invariant Audio-Visual Speech Enhancement in the Wild for Next-Generation Multi-Modal Hearing Aids","display_name":"Towards Pose-Invariant Audio-Visual Speech Enhancement in the Wild for Next-Generation Multi-Modal Hearing Aids","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4385478292","doi":"https://doi.org/10.1109/icasspw59220.2023.10192961"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw59220.2023.10192961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10192961","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://napier-repository.worktribe.com/file/3597086/1/Towards%20Pose-Invariant%20Audio-Visual%20Speech%20Enhancement%20in%20the%20Wild%20for%20Next-Generation%20Multi-Modal%20Hearing%20Aids%20%28accepted%20version%29","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068981769","display_name":"Mandar Gogate","orcid":"https://orcid.org/0000-0003-1712-9014"},"institutions":[{"id":"https://openalex.org/I251738","display_name":"Edinburgh Napier University","ror":"https://ror.org/03zjvnn91","country_code":"GB","type":"education","lineage":["https://openalex.org/I251738"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Mandar Gogate","raw_affiliation_strings":["Edinburgh Napier University,School of Computing,Scotland,UK","School of Computing, Edinburgh Napier University, Scotland, UK"],"affiliations":[{"raw_affiliation_string":"Edinburgh Napier University,School of Computing,Scotland,UK","institution_ids":["https://openalex.org/I251738"]},{"raw_affiliation_string":"School of Computing, Edinburgh Napier University, Scotland, UK","institution_ids":["https://openalex.org/I251738"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058869522","display_name":"Kia Dashtipour","orcid":"https://orcid.org/0000-0002-9651-6487"},"institutions":[{"id":"https://openalex.org/I251738","display_name":"Edinburgh Napier University","ror":"https://ror.org/03zjvnn91","country_code":"GB","type":"education","lineage":["https://openalex.org/I251738"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kia Dashtipour","raw_affiliation_strings":["Edinburgh Napier University,School of Computing,Scotland,UK","School of Computing, Edinburgh Napier University, Scotland, UK"],"affiliations":[{"raw_affiliation_string":"Edinburgh Napier University,School of Computing,Scotland,UK","institution_ids":["https://openalex.org/I251738"]},{"raw_affiliation_string":"School of Computing, Edinburgh Napier University, Scotland, UK","institution_ids":["https://openalex.org/I251738"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062211930","display_name":"Amir Hussain","orcid":"https://orcid.org/0000-0002-8080-082X"},"institutions":[{"id":"https://openalex.org/I251738","display_name":"Edinburgh Napier University","ror":"https://ror.org/03zjvnn91","country_code":"GB","type":"education","lineage":["https://openalex.org/I251738"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Amir Hussain","raw_affiliation_strings":["Edinburgh Napier University,School of Computing,Scotland,UK","School of Computing, Edinburgh Napier University, Scotland, UK"],"affiliations":[{"raw_affiliation_string":"Edinburgh Napier University,School of Computing,Scotland,UK","institution_ids":["https://openalex.org/I251738"]},{"raw_affiliation_string":"School of Computing, Edinburgh Napier University, Scotland, UK","institution_ids":["https://openalex.org/I251738"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068981769"],"corresponding_institution_ids":["https://openalex.org/I251738"],"apc_list":null,"apc_paid":null,"fwci":0.1962,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42557665,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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/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":0.9958000183105469,"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":0.9919999837875366,"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":0.7487931251525879},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6374866962432861},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5833479762077332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49873828887939453},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.49131980538368225},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4290695786476135},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.4286789894104004},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.4143562912940979},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2268662452697754},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10494622588157654}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7487931251525879},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6374866962432861},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5833479762077332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49873828887939453},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.49131980538368225},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4290695786476135},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.4286789894104004},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4143562912940979},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2268662452697754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10494622588157654},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","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/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icasspw59220.2023.10192961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10192961","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:repository@napier.ac.uk:3597086","is_oa":true,"landing_page_url":"http://researchrepository.napier.ac.uk/Output/3597086","pdf_url":"https://napier-repository.worktribe.com/file/3597086/1/Towards%20Pose-Invariant%20Audio-Visual%20Speech%20Enhancement%20in%20the%20Wild%20for%20Next-Generation%20Multi-Modal%20Hearing%20Aids%20%28accepted%20version%29","source":{"id":"https://openalex.org/S4306402591","display_name":"Edinburgh Napier Research Repository (Edinburgh Napier University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I251738","host_organization_name":"Edinburgh Napier University","host_organization_lineage":["https://openalex.org/I251738"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"}],"best_oa_location":{"id":"pmh:oai:repository@napier.ac.uk:3597086","is_oa":true,"landing_page_url":"http://researchrepository.napier.ac.uk/Output/3597086","pdf_url":"https://napier-repository.worktribe.com/file/3597086/1/Towards%20Pose-Invariant%20Audio-Visual%20Speech%20Enhancement%20in%20the%20Wild%20for%20Next-Generation%20Multi-Modal%20Hearing%20Aids%20%28accepted%20version%29","source":{"id":"https://openalex.org/S4306402591","display_name":"Edinburgh Napier Research Repository (Edinburgh Napier University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I251738","host_organization_name":"Edinburgh Napier University","host_organization_lineage":["https://openalex.org/I251738"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"},"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2193117753","display_name":"COG-MHEAR: Towards cognitively-inspired 5G-IoT enabled, multi-modal Hearing Aids","funder_award_id":"EP/T021063/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G2606664378","display_name":null,"funder_award_id":"COG-MHEAR","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8452545418","display_name":null,"funder_award_id":"unknown","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385478292.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1526392145","https://openalex.org/W1552314771","https://openalex.org/W2067295501","https://openalex.org/W2144404214","https://openalex.org/W2792764867","https://openalex.org/W2891205112","https://openalex.org/W2952218014","https://openalex.org/W2962134292","https://openalex.org/W2972513594","https://openalex.org/W2972541922","https://openalex.org/W3020804303","https://openalex.org/W3036526054","https://openalex.org/W3099330747","https://openalex.org/W3119796395","https://openalex.org/W3136499730","https://openalex.org/W3157352387","https://openalex.org/W3190965961","https://openalex.org/W4306933621","https://openalex.org/W6749825310","https://openalex.org/W6754420807","https://openalex.org/W6765401191","https://openalex.org/W6780140667","https://openalex.org/W6799838802"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W2073713056","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864"],"abstract_inverted_index":{"Classical":[0],"audio-visual":[1],"(AV)":[2],"speech":[3,19,67,74],"enhancement":[4],"(SE)":[5],"and":[6,21,35,55,65,75,107,124,143,152],"separation":[7,56],"methods":[8],"have":[9],"been":[10],"successful":[11],"at":[12],"operating":[13],"under":[14],"constrained":[15],"environments;":[16],"however,":[17],"the":[18,112,128,147],"quality":[20],"intelligibility":[22],"improvement":[23],"is":[24],"significantly":[25,133],"reduced":[26],"in":[27,33,150],"unconstrained":[28,51],"real-world":[29],"environments":[30],"where":[31],"variation":[32],"pose":[34],"illumination":[36],"are":[37,119],"encountered.":[38],"In":[39,78,126],"this":[40],"paper,":[41],"we":[42,80],"present":[43,81],"a":[44,82],"novel":[45],"privacy-preserving":[46],"approach":[47],"for":[48,94,121],"real":[49],"world":[50],"pose-invariant":[52,60,96,122],"AV":[53,97,130],"SE":[54,123,131,137],"that":[57,85,111],"contextually":[58],"exploits":[59],"3D":[61,115],"landmark":[62,116],"flow":[63,117],"features":[64,68,118],"noisy":[66],"to":[69],"selectively":[70],"suppress":[71],"unwanted":[72],"background":[73],"non-speech":[76],"noises.":[77],"addition,":[79,127],"unified":[83],"architecture":[84],"integrates":[86],"state-of-the-art":[87,135],"transformers":[88],"with":[89],"temporal":[90],"convolution":[91],"neural":[92],"networks":[93],"effective":[95,120],"SE.":[98],"The":[99],"preliminary":[100],"systematic":[101],"experimentation":[102],"on":[103],"benchmark":[104],"multi-pose":[105],"OuluVS2":[106],"LRS3-TED":[108],"corpora":[109],"demonstrate":[110],"privacy":[113],"preserving":[114],"separation.":[125],"proposed":[129,148],"model":[132,149],"outperforms":[134],"audio-only":[136],"model,":[138],"oracle":[139],"ideal":[140],"binary":[141],"mask,":[142],"A-only":[144],"variant":[145],"of":[146],"speaker":[151],"noise":[153],"independent":[154],"settings.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
