{"id":"https://openalex.org/W7135094949","doi":"https://doi.org/10.1016/j.specom.2026.103378","title":"AVFSNet: Audio-visual speech separation for flexible number of speakers with multi-scale and multi-task learning","display_name":"AVFSNet: Audio-visual speech separation for flexible number of speakers with multi-scale and multi-task learning","publication_year":2026,"publication_date":"2026-03-12","ids":{"openalex":"https://openalex.org/W7135094949","doi":"https://doi.org/10.1016/j.specom.2026.103378"},"language":"en","primary_location":{"id":"doi:10.1016/j.specom.2026.103378","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.specom.2026.103378","pdf_url":null,"source":{"id":"https://openalex.org/S128025751","display_name":"Speech Communication","issn_l":"0167-6393","issn":["0167-6393","1872-7182"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Communication","raw_type":"journal-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/A5006232137","display_name":"Daning Zhang","orcid":"https://orcid.org/0000-0002-1799-9901"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daning Zhang","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, 250061, Shandong Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, 250061, Shandong Province, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034561537","display_name":"Yuanjie Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanjie Deng","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, 250061, Shandong Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, 250061, Shandong Province, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128821479","display_name":"Ying Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]},{"id":"https://openalex.org/I4210106575","display_name":"Department of Science and Technology of Shandong Province","ror":"https://ror.org/01b9fvd84","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210106575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ying Wei","raw_affiliation_strings":["Industrial Technology Research Institte of Shandong Province, Jinan, 250102, Shandong Province, China","School of Control Science and Engineering, Shandong University, Jinan, 250061, Shandong Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Industrial Technology Research Institte of Shandong Province, Jinan, 250102, Shandong Province, China","institution_ids":["https://openalex.org/I4210106575"]},{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, 250061, Shandong Province, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084484593","display_name":"Bing Ji","orcid":"https://orcid.org/0000-0003-0034-6901"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Ji","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, 250061, Shandong Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, 250061, Shandong Province, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5128821479"],"corresponding_institution_ids":["https://openalex.org/I154099455","https://openalex.org/I4210106575"],"apc_list":{"value":2870,"currency":"USD","value_usd":2870},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3117632,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"179","issue":null,"first_page":"103378","last_page":"103378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9961000084877014,"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":0.9961000084877014,"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":0.000699999975040555,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.000699999975040555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.741599977016449},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6723999977111816},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6679999828338623},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6370999813079834},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.6139000058174133},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6104000210762024},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.536300003528595},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4383000135421753},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41830000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8108000159263611},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.741599977016449},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6723999977111816},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6679999828338623},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6579999923706055},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6370999813079834},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.6139000058174133},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6104000210762024},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.536300003528595},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4383000135421753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42899999022483826},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41830000281333923},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4050000011920929},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2793999910354614},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.258899986743927},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.specom.2026.103378","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.specom.2026.103378","pdf_url":null,"source":{"id":"https://openalex.org/S128025751","display_name":"Speech Communication","issn_l":"0167-6393","issn":["0167-6393","1872-7182"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Communication","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5144012530","display_name":null,"funder_award_id":"62171263","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/F4320326185","display_name":"Taishan Scholar Foundation of Shandong Province","ror":null},{"id":"https://openalex.org/F4320326189","display_name":"Taishan Scholar Project of Shandong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2756928350","https://openalex.org/W2808631503","https://openalex.org/W2890952074","https://openalex.org/W2898395910","https://openalex.org/W2946035067","https://openalex.org/W2952218014","https://openalex.org/W2960236182","https://openalex.org/W2962866211","https://openalex.org/W2963677766","https://openalex.org/W2972460025","https://openalex.org/W2972767900","https://openalex.org/W3081729342","https://openalex.org/W3096893582","https://openalex.org/W3097777922","https://openalex.org/W3119418740","https://openalex.org/W3173382920","https://openalex.org/W4289665794","https://openalex.org/W4295308317","https://openalex.org/W4366503942","https://openalex.org/W4406208517","https://openalex.org/W4409106262"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2026-03-13T00:00:00"}
