{"id":"https://openalex.org/W4403127009","doi":"https://doi.org/10.1109/iwaenc61483.2024.10693981","title":"Dynamic Audio-Visual Speech Enhancement using Recurrent Variational Autoencoders","display_name":"Dynamic Audio-Visual Speech Enhancement using Recurrent Variational Autoencoders","publication_year":2024,"publication_date":"2024-09-09","ids":{"openalex":"https://openalex.org/W4403127009","doi":"https://doi.org/10.1109/iwaenc61483.2024.10693981"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc61483.2024.10693981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10693981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","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/A5004014043","display_name":"Zohre Foroushi","orcid":"https://orcid.org/0000-0002-2801-7723"},"institutions":[{"id":"https://openalex.org/I67031392","display_name":"Carleton University","ror":"https://ror.org/02qtvee93","country_code":"CA","type":"education","lineage":["https://openalex.org/I67031392"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Z. Foroushi","raw_affiliation_strings":["Carleton University,Department of Systems & Computer Engineering,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carleton University,Department of Systems & Computer Engineering,Canada","institution_ids":["https://openalex.org/I67031392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001546768","display_name":"Richard M. Dansereau","orcid":"https://orcid.org/0000-0002-3512-3647"},"institutions":[{"id":"https://openalex.org/I67031392","display_name":"Carleton University","ror":"https://ror.org/02qtvee93","country_code":"CA","type":"education","lineage":["https://openalex.org/I67031392"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"R. M. Dansereau","raw_affiliation_strings":["Carleton University,Department of Systems & Computer Engineering,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carleton University,Department of Systems & Computer Engineering,Canada","institution_ids":["https://openalex.org/I67031392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I67031392"],"apc_list":null,"apc_paid":null,"fwci":1.6686,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.85524433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"60","last_page":"64"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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":0.9986000061035156,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9097999930381775,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9064000248908997,"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":0.734819769859314},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.713209867477417},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6581083536148071},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6494711637496948},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4350830614566803},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3956909477710724},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.22126784920692444},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.10561549663543701}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.734819769859314},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.713209867477417},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6581083536148071},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6494711637496948},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4350830614566803},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3956909477710724},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.22126784920692444},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.10561549663543701}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc61483.2024.10693981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10693981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2013608223","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2141998673","https://openalex.org/W2747876639","https://openalex.org/W2766672686","https://openalex.org/W2883322837","https://openalex.org/W2905196628","https://openalex.org/W2936446744","https://openalex.org/W2962866211","https://openalex.org/W2963082324","https://openalex.org/W2964058413","https://openalex.org/W2965390715","https://openalex.org/W3005621653","https://openalex.org/W3015791137","https://openalex.org/W3016011581","https://openalex.org/W3082851515","https://openalex.org/W3131332223","https://openalex.org/W3136499730","https://openalex.org/W3174264304","https://openalex.org/W4311841164","https://openalex.org/W6631190155"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398","https://openalex.org/W2775347418"],"abstract_inverted_index":{"Audio-visual":[0],"speech":[1,12,26,37,50,64,106,130],"enhancement":[2],"(AVSE)":[3],"has":[4,58],"emerged":[5],"as":[6],"a":[7,74,83],"promising":[8],"approach":[9,71],"to":[10,48,66,101],"enhance":[11],"perception":[13],"in":[14,25,62,122],"noisy":[15],"environments":[16],"by":[17],"leveraging":[18],"both":[19,73,94],"auditory":[20],"and":[21,82,96,133],"visual":[22,42,79],"cues":[23],"present":[24],"signals.":[27],"We":[28,52],"propose":[29],"an":[30],"audio-visual":[31,68],"recurrent":[32,84],"variational":[33],"autoencoder":[34],"(AV-RVAE)":[35],"for":[36,78,88],"enhancement.":[38],"This":[39],"model":[40],"incorporates":[41],"lip":[43],"motion":[44],"along":[45],"with":[46],"audio":[47],"improve":[49],"quality.":[51],"extend":[53],"the":[54,111],"RVAE":[55],"model,":[56],"which":[57],"shown":[59],"superior":[60],"performance":[61],"audio-only":[63],"enhancement,":[65],"handle":[67],"data.":[69,107],"Our":[70],"uses":[72],"dedicated":[75],"video":[76],"encoder":[77],"feature":[80],"extraction":[81],"neural":[85],"network":[86],"(RNN)":[87],"temporal":[89,103],"modeling.":[90],"Additionally,":[91],"we":[92],"introduce":[93],"causal":[95],"non-causal":[97],"variants":[98],"of":[99,105,129],"AV-RVAE":[100,116],"capture":[102],"dynamics":[104],"Experimental":[108],"results":[109],"on":[110],"NTCD-TIMIT":[112],"dataset":[113],"show":[114],"that":[115],"outperforms":[117],"existing":[118],"methods,":[119],"showing":[120],"improvements":[121],"scale-invariant":[123],"signal-to-distortion":[124],"ratio":[125],"(SISDR),":[126],"perceptual":[127],"evaluation":[128],"quality":[131],"(PESQ),":[132],"short-term":[134],"objective":[135],"intelligibility":[136],"(STOI)":[137],"metrics.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}