{"id":"https://openalex.org/W4283782204","doi":"https://doi.org/10.21437/interspeech.2022-10041","title":"Improving Visual Speech Enhancement Network by Learning Audio-visual Affinity with Multi-head Attention","display_name":"Improving Visual Speech Enhancement Network by Learning Audio-visual Affinity with Multi-head Attention","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283782204","doi":"https://doi.org/10.21437/interspeech.2022-10041"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10041","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10041","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5050125868","display_name":"Xinmeng Xu","orcid":"https://orcid.org/0009-0008-1607-7180"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Xinmeng Xu","raw_affiliation_strings":["E.E. Engineering, Trinity College Dublin, Ireland","vivo AI Lab, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"E.E. Engineering, Trinity College Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]},{"raw_affiliation_string":"vivo AI Lab, P.R. China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100322712","display_name":"Yan Wang","orcid":"https://orcid.org/0000-0002-5344-1884"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Wang","raw_affiliation_strings":["vivo AI Lab, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo AI Lab, P.R. China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043128749","display_name":"Jie Jia","orcid":"https://orcid.org/0000-0002-4516-4629"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Jia","raw_affiliation_strings":["vivo AI Lab, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo AI Lab, P.R. China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100687673","display_name":"Binbin Chen","orcid":"https://orcid.org/0000-0002-9584-0082"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Binbin Chen","raw_affiliation_strings":["vivo AI Lab, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo AI Lab, P.R. China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101706829","display_name":"Dejun Li","orcid":"https://orcid.org/0000-0002-1735-3713"},"institutions":[{"id":"https://openalex.org/I205016115","display_name":"Hubei University of Chinese Medicine","ror":"https://ror.org/02my3bx32","country_code":"CN","type":"education","lineage":["https://openalex.org/I205016115"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dejun Li","raw_affiliation_strings":["School of Foreign Languages, Hubei University of Chinese Medicine, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Foreign Languages, Hubei University of Chinese Medicine, P.R. China","institution_ids":["https://openalex.org/I205016115"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100687673"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4765,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84087471,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"971","last_page":"975"},"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/T11309","display_name":"Music and Audio Processing","score":0.9932000041007996,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9912999868392944,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7653721570968628},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6514135599136353},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5869839191436768},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5788843631744385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41211143136024475},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.18381071090698242}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7653721570968628},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6514135599136353},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5869839191436768},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5788843631744385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41211143136024475},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.18381071090698242},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10041","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10041","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1836465849","https://openalex.org/W1920741591","https://openalex.org/W2000916836","https://openalex.org/W2014621385","https://openalex.org/W2015143272","https://openalex.org/W2029199293","https://openalex.org/W2038010270","https://openalex.org/W2042407743","https://openalex.org/W2044893557","https://openalex.org/W2087681821","https://openalex.org/W2091930743","https://openalex.org/W2096779346","https://openalex.org/W2109349638","https://openalex.org/W2137400100","https://openalex.org/W2141998673","https://openalex.org/W2153894152","https://openalex.org/W2767290858","https://openalex.org/W2889442120","https://openalex.org/W2963082324","https://openalex.org/W2963285578","https://openalex.org/W2983423850","https://openalex.org/W3015785290","https://openalex.org/W3032514799","https://openalex.org/W3109018774","https://openalex.org/W3123318516","https://openalex.org/W3162493033","https://openalex.org/W3169133271","https://openalex.org/W4307196995"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128"],"abstract_inverted_index":{"Audio-visual":[0],"speech":[1,15,24,102],"enhancement":[2,103],"system":[3],"is":[4],"regarded":[5],"as":[6],"one":[7],"of":[8,16,134,142],"promising":[9],"solutions":[10],"for":[11,104],"isolating":[12],"and":[13,35,67,76,87,110],"enhancing":[14],"desired":[17],"speaker.Typical":[18],"methods":[19,37],"focus":[20],"on":[21],"predicting":[22],"clean":[23],"spectrum":[25],"via":[26],"a":[27,62,92],"naive":[28],"convolution":[29],"neural":[30],"network":[31,144],"based":[32],"encoderdecoder":[33],"architecture,":[34],"these":[36,57],"a)":[38,60],"are":[39,47,126,150],"not":[40],"adequate":[41],"to":[42,49,82,99,128],"use":[43],"data":[44],"fully,":[45],"b)":[46,90],"unable":[48],"effectively":[50],"balance":[51],"audio-visual":[52,80,101,108,117],"features.The":[53],"proposed":[54,136],"model":[55,63,137],"alleviates":[56],"drawbacks":[58],"by":[59,71],"applying":[61],"that":[64,77],"fuses":[65],"audio":[66],"visual":[68],"features":[69,81,109],"layer":[70,72,133],"in":[73,122],"encoding":[74],"phase,":[75],"feeds":[78],"fused":[79,107],"each":[83],"corresponding":[84],"decoder":[85],"layer,":[86],"more":[88],"importantly,":[89],"introducing":[91],"2-stage":[93],"multi-head":[94],"cross":[95],"attention":[96],"(MHCA)":[97],"mechanism":[98],"infer":[100],"balancing":[105],"the":[106,139,143,146],"eliminating":[111],"irrelevant":[112],"features.This":[113],"paper":[114],"proposes":[115],"attentional":[116],"multi-layer":[118],"feature":[119,129],"fusion":[120],"model,":[121],"which":[123],"MHCA":[124],"units":[125],"applied":[127],"mapping":[130],"at":[131],"every":[132],"decoder.The":[135],"demonstrates":[138],"superior":[140],"performance":[141],"against":[145],"state-of-the-art":[147],"models.Speech":[148],"samples":[149],"available":[151],"at:":[152],"https://XinmengXu.github.io/AVSE/AVCRN.html":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}