{"id":"https://openalex.org/W4372342911","doi":"https://doi.org/10.1109/icassp49357.2023.10094724","title":"Real-Time Audio-Visual End-To-End Speech Enhancement","display_name":"Real-Time Audio-Visual End-To-End Speech Enhancement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372342911","doi":"https://doi.org/10.1109/icassp49357.2023.10094724"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5041852728","display_name":"Zirun Zhu","orcid":"https://orcid.org/0000-0002-8898-6366"},"institutions":[{"id":"https://openalex.org/I4210092010","display_name":"EndoGastric Solutions (United States)","ror":"https://ror.org/00g35nv72","country_code":"US","type":"company","lineage":["https://openalex.org/I4210092010"]},{"id":"https://openalex.org/I4210109355","display_name":"OFM Research (United States)","ror":"https://ror.org/01xz1f624","country_code":"US","type":"company","lineage":["https://openalex.org/I4210109355"]},{"id":"https://openalex.org/I4210155201","display_name":"Redmond Fire Department","ror":"https://ror.org/05d788x61","country_code":"US","type":"government","lineage":["https://openalex.org/I4210155201"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zirun Zhu","raw_affiliation_strings":["Redmond,WA,USA","Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Redmond,WA,USA","institution_ids":["https://openalex.org/I4210092010","https://openalex.org/I4210109355"]},{"raw_affiliation_string":"Redmond, WA, USA","institution_ids":["https://openalex.org/I4210155201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023001621","display_name":"Hemin Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hemin Yang","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106627865","display_name":"Min Tang","orcid":"https://orcid.org/0009-0006-3428-9967"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Tang","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103178888","display_name":"Ziyi Yang","orcid":"https://orcid.org/0000-0001-9849-0180"},"institutions":[{"id":"https://openalex.org/I4210092010","display_name":"EndoGastric Solutions (United States)","ror":"https://ror.org/00g35nv72","country_code":"US","type":"company","lineage":["https://openalex.org/I4210092010"]},{"id":"https://openalex.org/I4210109355","display_name":"OFM Research (United States)","ror":"https://ror.org/01xz1f624","country_code":"US","type":"company","lineage":["https://openalex.org/I4210109355"]},{"id":"https://openalex.org/I4210155201","display_name":"Redmond Fire Department","ror":"https://ror.org/05d788x61","country_code":"US","type":"government","lineage":["https://openalex.org/I4210155201"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziyi Yang","raw_affiliation_strings":["Redmond,WA,USA","Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Redmond,WA,USA","institution_ids":["https://openalex.org/I4210092010","https://openalex.org/I4210109355"]},{"raw_affiliation_string":"Redmond, WA, USA","institution_ids":["https://openalex.org/I4210155201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026088950","display_name":"\u015eefik Emre Eskimez","orcid":"https://orcid.org/0000-0001-6259-5925"},"institutions":[{"id":"https://openalex.org/I4210092010","display_name":"EndoGastric Solutions (United States)","ror":"https://ror.org/00g35nv72","country_code":"US","type":"company","lineage":["https://openalex.org/I4210092010"]},{"id":"https://openalex.org/I4210109355","display_name":"OFM Research (United States)","ror":"https://ror.org/01xz1f624","country_code":"US","type":"company","lineage":["https://openalex.org/I4210109355"]},{"id":"https://openalex.org/I4210155201","display_name":"Redmond Fire Department","ror":"https://ror.org/05d788x61","country_code":"US","type":"government","lineage":["https://openalex.org/I4210155201"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sefik Emre Eskimez","raw_affiliation_strings":["Redmond,WA,USA","Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Redmond,WA,USA","institution_ids":["https://openalex.org/I4210092010","https://openalex.org/I4210109355"]},{"raw_affiliation_string":"Redmond, WA, USA","institution_ids":["https://openalex.org/I4210155201"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101528069","display_name":"Huaming Wang","orcid":"https://orcid.org/0000-0002-4434-7482"},"institutions":[{"id":"https://openalex.org/I4210092010","display_name":"EndoGastric Solutions (United States)","ror":"https://ror.org/00g35nv72","country_code":"US","type":"company","lineage":["https://openalex.org/I4210092010"]},{"id":"https://openalex.org/I4210109355","display_name":"OFM Research (United States)","ror":"https://ror.org/01xz1f624","country_code":"US","type":"company","lineage":["https://openalex.org/I4210109355"]},{"id":"https://openalex.org/I4210155201","display_name":"Redmond Fire Department","ror":"https://ror.org/05d788x61","country_code":"US","type":"government","lineage":["https://openalex.org/I4210155201"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaming Wang","raw_affiliation_strings":["Redmond,WA,USA","Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Redmond,WA,USA","institution_ids":["https://openalex.org/I4210092010","https://openalex.org/I4210109355"]},{"raw_affiliation_string":"Redmond, WA, USA","institution_ids":["https://openalex.org/I4210155201"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.175,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.90534208,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.8155251741409302},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6892780065536499},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5453634858131409},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5004029273986816},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4232829511165619},{"id":"https://openalex.org/keywords/end-user","display_name":"End user","score":0.420575886964798},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2225407063961029},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.20921316742897034},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19043657183647156},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.08648821711540222},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.07078388333320618}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8155251741409302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6892780065536499},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5453634858131409},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5004029273986816},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4232829511165619},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.420575886964798},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2225407063961029},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.20921316742897034},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19043657183647156},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.08648821711540222},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.07078388333320618}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":34,"referenced_works":["https://openalex.org/W2016053056","https://openalex.org/W2194775991","https://openalex.org/W2593116425","https://openalex.org/W2770119437","https://openalex.org/W2808631503","https://openalex.org/W2883780447","https://openalex.org/W2891205112","https://openalex.org/W2908510526","https://openalex.org/W2963082324","https://openalex.org/W2963446712","https://openalex.org/W2964171275","https://openalex.org/W2973062255","https://openalex.org/W2998161426","https://openalex.org/W3011424113","https://openalex.org/W3015612952","https://openalex.org/W3015785290","https://openalex.org/W3016011581","https://openalex.org/W3020804303","https://openalex.org/W3024147341","https://openalex.org/W3035570025","https://openalex.org/W3095248373","https://openalex.org/W3120903390","https://openalex.org/W3162707322","https://openalex.org/W3198543387","https://openalex.org/W3206706278","https://openalex.org/W4226185896","https://openalex.org/W4283782204","https://openalex.org/W4283837854","https://openalex.org/W4289665794","https://openalex.org/W4382202943","https://openalex.org/W6746278845","https://openalex.org/W6755462816","https://openalex.org/W6757817989","https://openalex.org/W6777214184"],"related_works":["https://openalex.org/W4299590256","https://openalex.org/W3163634122","https://openalex.org/W3119482857","https://openalex.org/W2919182614","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2166381389","https://openalex.org/W2275432853","https://openalex.org/W4393280045","https://openalex.org/W2054736184"],"abstract_inverted_index":{"Audio-visual":[0],"speech":[1,23],"enhancement":[2,24,58,67],"(AV-SE)":[3],"methods":[4],"utilize":[5],"auxiliary":[6],"visual":[7,118],"cues":[8],"to":[9,19,83,114],"enhance":[10],"speakers\u2019":[11],"voices.":[12],"Therefore,":[13],"technically":[14],"they":[15],"should":[16],"be":[17],"able":[18],"outperform":[20],"the":[21,33,63,85,90,98,102,124,134],"audio-only":[22],"(SE)":[25],"methods.":[26],"However,":[27],"there":[28],"are":[29],"few":[30],"works":[31],"in":[32,42],"literature":[34],"on":[35,45,62,101],"an":[36],"AV-SE":[37,103],"system":[38],"that":[39,123],"can":[40],"work":[41],"real":[43],"time":[44],"a":[46,53,79,108,139],"CPU.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51],"propose":[52,107],"low-latency":[54],"real-time":[55],"audio-visual":[56],"end-to-end":[57,66],"(AV-E3Net)":[59],"model":[60,92,126,137],"based":[61],"recently":[64],"proposed":[65,125],"network":[68],"(E3Net).":[69],"Our":[70,120],"main":[71],"contribution":[72],"includes":[73],"two":[74],"aspects:":[75],"1)":[76],"We":[77,106],"employ":[78],"dense":[80],"connection":[81],"module":[82,95,113],"solve":[84],"performance":[86,100],"degradation":[87],"caused":[88],"by":[89],"deep":[91],"structure.":[93],"This":[94],"significantly":[96],"improves":[97],"model\u2019s":[99],"task.":[104],"2)":[105],"multi-stage":[109],"gating-and-summation":[110],"(GS)":[111],"fusion":[112],"merge":[115],"audio":[116],"and":[117,131],"cues.":[119],"results":[121],"show":[122],"provides":[127],"better":[128],"perceptual":[129],"quality":[130],"intelligibility":[132],"than":[133],"baseline":[135],"E3net":[136],"with":[138],"negligible":[140],"computational":[141],"cost":[142],"increase.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}