{"id":"https://openalex.org/W3015612952","doi":"https://doi.org/10.1109/icassp40776.2020.9054528","title":"AV(SE)<sup>2</sup>: Audio-Visual Squeeze-Excite Speech Enhancement","display_name":"AV(SE)<sup>2</sup>: Audio-Visual Squeeze-Excite Speech Enhancement","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015612952","doi":"https://doi.org/10.1109/icassp40776.2020.9054528","mag":"3015612952"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5030257576","display_name":"Michael L. Iuzzolino","orcid":"https://orcid.org/0009-0006-6445-736X"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael L. Iuzzolino","raw_affiliation_strings":["University of Colorado Boulder, Boulder, CO, USA"],"affiliations":[{"raw_affiliation_string":"University of Colorado Boulder, Boulder, CO, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084879161","display_name":"Kazuhito Koishida","orcid":"https://orcid.org/0000-0002-3111-5375"},"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":"Kazuhito Koishida","raw_affiliation_strings":["Microsoft Corporation, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5030257576"],"corresponding_institution_ids":["https://openalex.org/I188538660"],"apc_list":null,"apc_paid":null,"fwci":1.8288,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.85568494,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7539","last_page":"7543"},"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":0.9932000041007996,"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/T11309","display_name":"Music and Audio Processing","score":0.9907000064849854,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7938979864120483},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6894822120666504},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6298213005065918},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.587480902671814},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.46914544701576233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4602043330669403},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38023316860198975},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1603955626487732}],"concepts":[{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7938979864120483},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6894822120666504},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6298213005065918},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.587480902671814},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.46914544701576233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4602043330669403},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38023316860198975},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1603955626487732},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W304179306","https://openalex.org/W1518556865","https://openalex.org/W1882423120","https://openalex.org/W1991139021","https://openalex.org/W2007997516","https://openalex.org/W2016053056","https://openalex.org/W2052666245","https://openalex.org/W2070707809","https://openalex.org/W2103082677","https://openalex.org/W2141998673","https://openalex.org/W2154754161","https://openalex.org/W2159202424","https://openalex.org/W2194775991","https://openalex.org/W2476548250","https://openalex.org/W2559809918","https://openalex.org/W2787579267","https://openalex.org/W2788241093","https://openalex.org/W2808631503","https://openalex.org/W2901702433","https://openalex.org/W2946035067","https://openalex.org/W2949662773","https://openalex.org/W2962754210","https://openalex.org/W2963082324","https://openalex.org/W2963307811","https://openalex.org/W2963420686","https://openalex.org/W2963528589","https://openalex.org/W2964171275","https://openalex.org/W2972513594","https://openalex.org/W2972612102","https://openalex.org/W3104792420","https://openalex.org/W4289665794","https://openalex.org/W6743555153","https://openalex.org/W6743731764","https://openalex.org/W6748655329","https://openalex.org/W6749863746","https://openalex.org/W6766752837"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W3095575180","https://openalex.org/W2389596151","https://openalex.org/W4221148444","https://openalex.org/W4226054107","https://openalex.org/W4387678054","https://openalex.org/W4306784355","https://openalex.org/W2784004155","https://openalex.org/W4246226292","https://openalex.org/W2150768546"],"abstract_inverted_index":{"The":[0,57],"goal":[1],"of":[2,29,66,84,89,108],"audio-visual":[3,39],"speech":[4,31,50],"enhancement":[5],"(AVSE)":[6],"is":[7,60],"to":[8,21,62,79],"supplement":[9],"audio-only":[10],"information":[11],"with":[12,98],"visual":[13,70],"information,":[14],"such":[15],"as":[16,77],"target":[17],"speaker's":[18],"lip":[19],"movements,":[20],"improve":[22],"the":[23,67],"intelligibility":[24],"and":[25,69,72],"overall":[26],"perceptual":[27],"quality":[28],"noisy":[30],"signals.":[32],"We":[33,91],"propose":[34],"a":[35,44],"new":[36],"mechanism":[37],"for":[38,49],"(AV)":[40],"fusion":[41,58,82,113],"that":[42,93],"leverages":[43],"cross-modal":[45],"squeeze-excitation":[46],"(SE)":[47],"block":[48,59],"enhancement:":[51],"AV(SE)":[52,94],"<sup":[53,95],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[54,96],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[55,97],".":[56],"adaptable":[61],"any":[63],"feature":[64,103],"layer":[65],"audio":[68],"networks":[71],"significantly":[73],"reduces":[74],"model":[75],"parameters":[76],"compared":[78],"standard":[80],"AV":[81,112],"methods":[83,107],"channel-wise":[85,110],"concatenation":[86],"without":[87],"loss":[88],"performance.":[90],"show":[92],"time-based":[99],"gating":[100],"across":[101],"multiple":[102],"layers":[104],"outperforms":[105],"baseline":[106],"single-point,":[109],"concatenated":[111],"on":[114],"objective":[115],"evaluations.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}
