{"id":"https://openalex.org/W4214567298","doi":"https://doi.org/10.1109/taslp.2022.3153265","title":"Improved Lite Audio-Visual Speech Enhancement","display_name":"Improved Lite Audio-Visual Speech Enhancement","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4214567298","doi":"https://doi.org/10.1109/taslp.2022.3153265"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3153265","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3153265","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/taslp.2022.3153265","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033696869","display_name":"Shang-Yi Chuang","orcid":"https://orcid.org/0000-0002-8824-096X"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shang-Yi Chuang","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-8824-096X","affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-3599-5071","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-6956-0418","affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1006,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.94909283,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"30","issue":null,"first_page":"1345","last_page":"1359"},"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":0.9965000152587891,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9937000274658203,"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/computer-science","display_name":"Computer science","score":0.8528496623039246},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7205857038497925},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6908787488937378},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5290027260780334},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4821281433105469},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.46381208300590515},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44164618849754333},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.4391224682331085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41586992144584656},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.23556524515151978},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1637604534626007},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10708880424499512}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8528496623039246},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7205857038497925},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6908787488937378},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5290027260780334},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4821281433105469},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46381208300590515},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44164618849754333},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.4391224682331085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41586992144584656},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.23556524515151978},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1637604534626007},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10708880424499512},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3153265","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3153265","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2022.3153265","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3153265","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.550000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1182361818","display_name":null,"funder_award_id":"110-2634-F-002-047","funder_id":"https://openalex.org/F4320322108","funder_display_name":"Ministry of Science and Technology"},{"id":"https://openalex.org/G4187474199","display_name":null,"funder_award_id":"109-2634-F-008-006","funder_id":"https://openalex.org/F4320322108","funder_display_name":"Ministry of Science and Technology"},{"id":"https://openalex.org/G4621929662","display_name":null,"funder_award_id":"109-2221-E-001-016","funder_id":"https://openalex.org/F4320322108","funder_display_name":"Ministry of Science and Technology"},{"id":"https://openalex.org/G7579904835","display_name":null,"funder_award_id":"109-2218-E-011-010","funder_id":"https://openalex.org/F4320322108","funder_display_name":"Ministry of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320322108","display_name":"Ministry of Science and Technology","ror":"https://ror.org/032e49973"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":103,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1552314771","https://openalex.org/W1868815422","https://openalex.org/W1897240248","https://openalex.org/W1901129140","https://openalex.org/W1963950237","https://openalex.org/W1964509438","https://openalex.org/W1966264494","https://openalex.org/W1974204068","https://openalex.org/W1975301756","https://openalex.org/W1984634380","https://openalex.org/W1999977067","https://openalex.org/W2000916836","https://openalex.org/W2013608223","https://openalex.org/W2035777533","https://openalex.org/W2041925401","https://openalex.org/W2044893557","https://openalex.org/W2060207914","https://openalex.org/W2075731813","https://openalex.org/W2084043065","https://openalex.org/W2094461119","https://openalex.org/W2100913683","https://openalex.org/W2105594594","https://openalex.org/W2109349638","https://openalex.org/W2109762775","https://openalex.org/W2115252128","https://openalex.org/W2116756305","https://openalex.org/W2125114513","https://openalex.org/W2130476329","https://openalex.org/W2130789253","https://openalex.org/W2141998673","https://openalex.org/W2145962650","https://openalex.org/W2153894152","https://openalex.org/W2155041441","https://openalex.org/W2163101527","https://openalex.org/W2164098335","https://openalex.org/W2194775991","https://openalex.org/W2291877678","https://openalex.org/W2304609584","https://openalex.org/W2326115863","https://openalex.org/W2400006663","https://openalex.org/W2402901296","https://openalex.org/W2405774341","https://openalex.org/W2408688265","https://openalex.org/W2489547515","https://openalex.org/W2491992013","https://openalex.org/W2527611302","https://openalex.org/W2550397165","https://openalex.org/W2577762507","https://openalex.org/W2584393883","https://openalex.org/W2594345168","https://openalex.org/W2604379605","https://openalex.org/W2605589342","https://openalex.org/W2746457594","https://openalex.org/W2755891984","https://openalex.org/W2774389566","https://openalex.org/W2774812352","https://openalex.org/W2788241093","https://openalex.org/W2886564777","https://openalex.org/W2889597349","https://openalex.org/W2891226622","https://openalex.org/W2918296821","https://openalex.org/W2920977479","https://openalex.org/W2938395714","https://openalex.org/W2943554574","https://openalex.org/W2962753325","https://openalex.org/W2962866211","https://openalex.org/W2962935966","https://openalex.org/W2963082324","https://openalex.org/W2963192057","https://openalex.org/W2963341071","https://openalex.org/W2965390715","https://openalex.org/W2971630540","https://openalex.org/W2978471304","https://openalex.org/W2983423850","https://openalex.org/W2990078986","https://openalex.org/W2991251958","https://openalex.org/W3003337611","https://openalex.org/W3004146833","https://openalex.org/W3008400075","https://openalex.org/W3011424113","https://openalex.org/W3014522660","https://openalex.org/W3015358918","https://openalex.org/W3015893539","https://openalex.org/W3016129867","https://openalex.org/W3033703941","https://openalex.org/W3094612121","https://openalex.org/W3094932283","https://openalex.org/W3096028031","https://openalex.org/W3096408984","https://openalex.org/W3096509852","https://openalex.org/W3102334822","https://openalex.org/W3104019135","https://openalex.org/W3136499730","https://openalex.org/W4289665794","https://openalex.org/W6607895473","https://openalex.org/W6629006327","https://openalex.org/W6631190155","https://openalex.org/W6677618333","https://openalex.org/W6739901393","https://openalex.org/W6748319235","https://openalex.org/W6766978945","https://openalex.org/W6796469999"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W111365173","https://openalex.org/W2161396743","https://openalex.org/W2386453889","https://openalex.org/W3134790285"],"abstract_inverted_index":{"Numerous":[0],"studies":[1],"have":[2],"investigated":[3],"the":[4,29,64,93,123,131,151],"effectiveness":[5],"of":[6,31,96],"audio-visual":[7,40,100,174],"multimodal":[8],"learning":[9],"for":[10,45,169],"speech":[11,33,41,134],"enhancement":[12,42,159],"(AVSE)":[13],"tasks,":[14],"seeking":[15],"a":[16,38,46,116],"solution":[17],"that":[18,141,165],"uses":[19,115],"visual":[20,98,104],"data":[21],"as":[22,122],"auxiliary":[23],"and":[24,59,102,156],"complementary":[25],"input":[26],"to":[27,50,60,77,81,143],"reduce":[28],"noise":[30],"noisy":[32],"signals.":[34],"Recently,":[35],"we":[36,74],"proposed":[37,107],"lite":[39],"(LAVSE)":[43],"algorithm":[44],"car-driving":[47],"scenario.":[48],"Compared":[49],"conventional":[51,144],"AVSE":[52,90,125,145],"systems,":[53,91,146],"LAVSE":[54,76,112],"requires":[55],"less":[56],"online":[57],"computation":[58],"some":[61],"extent":[62],"solves":[63],"user":[65],"privacy":[66],"problem":[67],"on":[68,130],"facial":[69],"data.":[70,105],"In":[71],"this":[72],"study,":[73],"extend":[75],"improve":[78,158],"its":[79],"ability":[80],"address":[82],"three":[83,153],"practical":[84,154],"issues":[85,155],"often":[86],"encountered":[87],"in":[88],"implementing":[89],"namely,":[92],"additional":[94],"cost":[95],"processing":[97],"data,":[99],"asynchronization,":[101],"low-quality":[103],"The":[106,161],"system":[108],"is":[109,167],"termed":[110],"improved":[111],"(iLAVSE),":[113],"which":[114],"convolutional":[117],"recurrent":[118],"neural":[119],"network":[120],"architecture":[121],"core":[124],"model.":[126],"We":[127],"evaluate":[128],"iLAVSE":[129,147,166],"Taiwan":[132],"Mandarin":[133],"with":[135],"video":[136],"dataset.":[137],"Experimental":[138],"results":[139,162],"confirm":[140,164],"compared":[142],"can":[148,157],"effectively":[149],"overcome":[150],"aforementioned":[152],"performance.":[160],"also":[163],"suitable":[168],"real-world":[170],"scenarios,":[171],"where":[172],"high-quality":[173],"sensors":[175],"may":[176],"not":[177],"always":[178],"be":[179],"available.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}