{"id":"https://openalex.org/W4308233949","doi":"https://doi.org/10.1109/icip46576.2022.9897739","title":"Visual Sound Source Separation with Partial Supervision Learning","display_name":"Visual Sound Source Separation with Partial Supervision Learning","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308233949","doi":"https://doi.org/10.1109/icip46576.2022.9897739"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897739","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","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":"2022 IEEE International Conference on Image Processing (ICIP)","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/A5066785269","display_name":"Huasen Wang","orcid":"https://orcid.org/0000-0002-7327-282X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huasen Wang","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Comp. Sci. and Engin","School of Comp. Sci. and Engin., University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Comp. Sci. and Engin","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Comp. Sci. and Engin., University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001474971","display_name":"Lingling Gao","orcid":"https://orcid.org/0000-0002-4521-8703"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingling Gao","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Comp. Sci. and Engin","School of Comp. Sci. and Engin., University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Comp. Sci. and Engin","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Comp. Sci. and Engin., University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032643844","display_name":"Qianchao Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianchao Tan","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Comp. Sci. and Engin","School of Comp. Sci. and Engin., University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Comp. Sci. and Engin","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Comp. Sci. and Engin., University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036253906","display_name":"Luping Ji","orcid":"https://orcid.org/0000-0002-1200-5218"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luping Ji","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Comp. Sci. and Engin","School of Comp. Sci. and Engin., University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Comp. Sci. and Engin","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Comp. Sci. and Engin., University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11965342,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"2127","last_page":"2131"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9962999820709229,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9943000078201294,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7902899980545044},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6287315487861633},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6167784929275513},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6016566157341003},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5934406518936157},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5669089555740356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5314328670501709},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5200714468955994},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4630233645439148},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4084673225879669},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3599466383457184},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.19258546829223633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7902899980545044},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6287315487861633},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6167784929275513},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6016566157341003},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5934406518936157},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5669089555740356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5314328670501709},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5200714468955994},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4630233645439148},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4084673225879669},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3599466383457184},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.19258546829223633},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip46576.2022.9897739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897739","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","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":"2022 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1901129140","https://openalex.org/W2150415460","https://openalex.org/W2194775991","https://openalex.org/W2295107390","https://openalex.org/W2404400936","https://openalex.org/W2587994092","https://openalex.org/W2884585870","https://openalex.org/W2962865004","https://openalex.org/W2963218389","https://openalex.org/W2981816492","https://openalex.org/W2981851635","https://openalex.org/W2988200020","https://openalex.org/W3017343282","https://openalex.org/W3096780661","https://openalex.org/W3105352633","https://openalex.org/W3109606338","https://openalex.org/W3157866890","https://openalex.org/W3169318522","https://openalex.org/W3173382920","https://openalex.org/W3182657421","https://openalex.org/W6620707391","https://openalex.org/W6733667431","https://openalex.org/W6783539077"],"related_works":["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","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2077498359"],"abstract_inverted_index":{"Recent":[0],"deep":[1],"learning":[2,51],"approaches":[3],"have":[4],"achieved":[5],"impressive":[6],"performance":[7,62],"in":[8,130],"visually-guided":[9],"sound":[10,35,132],"source":[11,36],"separation":[12,61],"tasks.":[13],"However,":[14],"due":[15],"to":[16,33,58,91,103],"the":[17,30,60,80,88],"lack":[18],"of":[19,63,82],"real-world":[20,41,64,77,93],"mixed/separated":[21],"audio":[22],"sample":[23],"pairs,":[24],"most":[25],"methods":[26],"seriously":[27],"rely":[28],"on":[29,111],"\"Mix-and-Separate\"":[31],"manner":[32],"learn":[34,104],"separation,":[37],"often":[38,125],"unsuitable":[39],"for":[40],"mixtures.":[42,78],"To":[43,79],"address":[44],"this":[45,67,85],"issue,":[46],"we":[47],"utilize":[48],"a":[49,98],"semi-supervised":[50],"technique":[52],"\u2014":[53,57],"preserving":[54],"audio-visual":[55,105],"consistency":[56],"improve":[59,92],"scenarios.":[65],"In":[66],"way,":[68],"our":[69,83,122],"network":[70],"is":[71],"trained":[72],"jointly":[73],"by":[74],"artificial":[75],"and":[76,116],"best":[81],"knowledge,":[84],"could":[86,124],"be":[87],"first":[89],"attempt":[90],"generalization.":[94],"We":[95],"also":[96],"design":[97],"category-guided":[99],"audiovisual":[100],"fusion":[101],"module":[102],"matching.":[106],"Comparative":[107],"experiments":[108],"are":[109],"performed":[110],"two":[112],"publicly-available":[113],"datasets,":[114],"MUSIC":[115],"AudioSet.":[117],"Experiment":[118],"results":[119],"demonstrate":[120],"that":[121],"method":[123],"outperform":[126],"other":[127],"state-of-the-art":[128],"ones":[129],"visual":[131],"separation.":[133]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}