{"id":"https://openalex.org/W4387976339","doi":"https://doi.org/10.3390/s23218770","title":"A Facial Feature and Lip Movement Enhanced Audio-Visual Speech Separation Model","display_name":"A Facial Feature and Lip Movement Enhanced Audio-Visual Speech Separation Model","publication_year":2023,"publication_date":"2023-10-27","ids":{"openalex":"https://openalex.org/W4387976339","doi":"https://doi.org/10.3390/s23218770","pmid":"https://pubmed.ncbi.nlm.nih.gov/37960477"},"language":"en","primary_location":{"id":"doi:10.3390/s23218770","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23218770","pdf_url":"https://www.mdpi.com/1424-8220/23/21/8770/pdf?version=1698413672","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/23/21/8770/pdf?version=1698413672","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025571788","display_name":"Guizhu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guizhu Li","raw_affiliation_strings":["College of Electronic Engineering, Ocean University of China, Qingdao 266100, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electronic Engineering, Ocean University of China, Qingdao 266100, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101640188","display_name":"Min Fu","orcid":"https://orcid.org/0000-0003-1413-3325"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Min Fu","raw_affiliation_strings":["College of Electronic Engineering, Ocean University of China, Qingdao 266100, China","Sanya Oceanography Institution, Ocean University of China, Sanya 572024, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electronic Engineering, Ocean University of China, Qingdao 266100, China","institution_ids":["https://openalex.org/I59028903"]},{"raw_affiliation_string":"Sanya Oceanography Institution, Ocean University of China, Sanya 572024, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044418167","display_name":"Mengnan Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengnan Sun","raw_affiliation_strings":["College of Electronic Engineering, Ocean University of China, Qingdao 266100, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electronic Engineering, Ocean University of China, Qingdao 266100, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400563","display_name":"Xuefeng Liu","orcid":"https://orcid.org/0000-0003-2705-8731"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefeng Liu","raw_affiliation_strings":["College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao 266061, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao 266061, China","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101974805","display_name":"Bing Zheng","orcid":"https://orcid.org/0000-0003-2295-3569"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Zheng","raw_affiliation_strings":["College of Electronic Engineering, Ocean University of China, Qingdao 266100, China","Sanya Oceanography Institution, Ocean University of China, Sanya 572024, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electronic Engineering, Ocean University of China, Qingdao 266100, China","institution_ids":["https://openalex.org/I59028903"]},{"raw_affiliation_string":"Sanya Oceanography Institution, Ocean University of China, Sanya 572024, China","institution_ids":["https://openalex.org/I59028903"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101640188"],"corresponding_institution_ids":["https://openalex.org/I59028903"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":0.3479,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54856959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"23","issue":"21","first_page":"8770","last_page":"8770"},"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":0.9919000267982483,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.991100013256073,"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":0.7659860849380493},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6940538287162781},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6494415998458862},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6186270117759705},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5665682554244995},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5488911867141724},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5066478848457336},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4839487373828888},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.46222221851348877},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44633209705352783},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14955830574035645},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.12502676248550415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7659860849380493},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6940538287162781},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6494415998458862},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6186270117759705},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5665682554244995},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5488911867141724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5066478848457336},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4839487373828888},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.46222221851348877},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44633209705352783},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14955830574035645},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.12502676248550415},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D003463","descriptor_name":"Cues","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003463","descriptor_name":"Cues","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003463","descriptor_name":"Cues","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008046","descriptor_name":"Lip","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008046","descriptor_name":"Lip","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008046","descriptor_name":"Lip","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009068","descriptor_name":"Movement","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009068","descriptor_name":"Movement","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009068","descriptor_name":"Movement","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.3390/s23218770","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23218770","pdf_url":"https://www.mdpi.com/1424-8220/23/21/8770/pdf?version=1698413672","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:37960477","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37960477","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10647675","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10647675","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10647675/pdf/sensors-23-08770.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:5b5dbac7b8a94976b5c93d3dde7e5a6f","is_oa":true,"landing_page_url":"https://doaj.org/article/5b5dbac7b8a94976b5c93d3dde7e5a6f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 23, Iss 21, p 8770 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/s23218770","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23218770","pdf_url":"https://www.mdpi.com/1424-8220/23/21/8770/pdf?version=1698413672","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3248542210","display_name":"\u57fa\u4e8e\u52a8\u6001\u968f\u673a\u5171\u632f\u548c\u53c2\u6570\u4f18\u5316\u5377\u79ef\u795e\u7ecf\u7f51\u7edc\u7684\u9ad8\u5149\u8c31\u56fe\u50cf\u5206\u7c7b\u7814\u7a76","funder_award_id":"61971253","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6849302237","display_name":null,"funder_award_id":"ZR2020MF011","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G848024145","display_name":null,"funder_award_id":"ZDKJ202017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4387976339.pdf"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1790748249","https://openalex.org/W1882423120","https://openalex.org/W1901129140","https://openalex.org/W1977812963","https://openalex.org/W1991139021","https://openalex.org/W2034040413","https://openalex.org/W2044222806","https://openalex.org/W2079362249","https://openalex.org/W2081144555","https://openalex.org/W2082183045","https://openalex.org/W2086139506","https://openalex.org/W2096733369","https://openalex.org/W2124149378","https://openalex.org/W2141998673","https://openalex.org/W2194775991","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2551572271","https://openalex.org/W2558649592","https://openalex.org/W2678916739","https://openalex.org/W2735663686","https://openalex.org/W2752782242","https://openalex.org/W2808631503","https://openalex.org/W2844030168","https://openalex.org/W2883780447","https://openalex.org/W2884585870","https://openalex.org/W2907750714","https://openalex.org/W2938917877","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962866211","https://openalex.org/W2962935966","https://openalex.org/W2963125010","https://openalex.org/W2963420686","https://openalex.org/W3008400075","https://openalex.org/W3015445830","https://openalex.org/W3016011581","https://openalex.org/W3099330747","https://openalex.org/W3124794156","https://openalex.org/W3124972797","https://openalex.org/W3160244659","https://openalex.org/W3160672713","https://openalex.org/W3182657421","https://openalex.org/W4210583256","https://openalex.org/W4289665794","https://openalex.org/W4312095954"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W4245955731","https://openalex.org/W2393726419","https://openalex.org/W2380912101","https://openalex.org/W2972212393","https://openalex.org/W2132337154"],"abstract_inverted_index":{"The":[0],"cocktail":[1],"party":[2],"problem":[3],"can":[4],"be":[5],"more":[6],"effectively":[7],"addressed":[8],"by":[9],"leveraging":[10],"the":[11,24,42,52,59,67,75,84,88,95,105,111],"speaker's":[12],"visual":[13,29,100],"and":[14,33,99,118],"audio":[15,43,98],"information.":[16,82],"This":[17],"paper":[18],"proposes":[19],"a":[20,63],"method":[21],"to":[22,46,78,91],"improve":[23],"audio's":[25],"separation":[26,44],"using":[27],"two":[28],"cues:":[30],"facial":[31],"features":[32],"lip":[34],"movement.":[35],"Firstly,":[36],"residual":[37],"connections":[38],"are":[39],"introduced":[40],"in":[41,74,124],"module":[45,77],"extract":[47],"detailed":[48],"features.":[49],"Secondly,":[50],"considering":[51],"video":[53],"stream":[54],"contains":[55],"information":[56],"other":[57],"than":[58],"face,":[60],"which":[61],"has":[62],"minimal":[64],"correlation":[65],"with":[66],"audio,":[68],"an":[69],"attention":[70],"mechanism":[71],"is":[72],"employed":[73],"face":[76],"focus":[79],"on":[80,104],"crucial":[81],"Then,":[83],"loss":[85],"function":[86],"considers":[87],"audio-visual":[89],"similarity":[90],"take":[92],"advantage":[93],"of":[94],"relationship":[96],"between":[97],"completely.":[101],"Experimental":[102],"results":[103],"public":[106],"VoxCeleb2":[107],"dataset":[108],"show":[109],"that":[110],"proposed":[112],"model":[113],"significantly":[114],"enhanced":[115],"SDR,":[116],"PSEQ,":[117],"STOI,":[119],"especially":[120],"4":[121],"dB":[122],"improvements":[123],"SDR.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
