{"id":"https://openalex.org/W4376630663","doi":"https://doi.org/10.3390/s23094540","title":"Off-Screen Sound Separation Based on Audio-visual Pre-training Using Binaural Audio","display_name":"Off-Screen Sound Separation Based on Audio-visual Pre-training Using Binaural Audio","publication_year":2023,"publication_date":"2023-05-07","ids":{"openalex":"https://openalex.org/W4376630663","doi":"https://doi.org/10.3390/s23094540","pmid":"https://pubmed.ncbi.nlm.nih.gov/37177744"},"language":"en","primary_location":{"id":"doi:10.3390/s23094540","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23094540","pdf_url":"https://www.mdpi.com/1424-8220/23/9/4540/pdf?version=1683529443","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/1424-8220/23/9/4540/pdf?version=1683529443","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006800515","display_name":"Masaki Yoshida","orcid":"https://orcid.org/0000-0002-8746-1533"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masaki Yoshida","raw_affiliation_strings":["Graduate School of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan"],"raw_orcid":"https://orcid.org/0000-0002-8746-1533","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002757875","display_name":"Ren Togo","orcid":"https://orcid.org/0000-0002-4474-3995"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ren Togo","raw_affiliation_strings":["Faculty of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4474-3995","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009032240","display_name":"Takahiro Ogawa","orcid":"https://orcid.org/0000-0001-5332-8112"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Ogawa","raw_affiliation_strings":["Faculty of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5332-8112","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":null,"display_name":"Miki Haseyama","orcid":"https://orcid.org/0000-0003-1496-1761"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Miki Haseyama","raw_affiliation_strings":["Faculty of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1496-1761","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, N-14, W-9, Kita-ku, Sapporo 060-0814, Hokkaido, Japan","institution_ids":["https://openalex.org/I205349734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205349734"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2673},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2673},"fwci":0.4009,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.53799803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"23","issue":"9","first_page":"4540","last_page":"4540"},"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.9975000023841858,"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/binaural-recording","display_name":"Binaural recording","score":0.7490165829658508},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7079732418060303},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5557931065559387},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5462139248847961},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5431851148605347},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5405060648918152},{"id":"https://openalex.org/keywords/surround-sound","display_name":"Surround sound","score":0.5330860614776611},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.5079138875007629},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4713515639305115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40323567390441895},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3913891315460205},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.24030661582946777},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1865403950214386},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07948571443557739}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.7490165829658508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7079732418060303},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5557931065559387},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5462139248847961},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5431851148605347},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5405060648918152},{"id":"https://openalex.org/C2780544925","wikidata":"https://www.wikidata.org/wiki/Q569874","display_name":"Surround sound","level":3,"score":0.5330860614776611},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.5079138875007629},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4713515639305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40323567390441895},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3913891315460205},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.24030661582946777},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1865403950214386},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07948571443557739},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3390/s23094540","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23094540","pdf_url":"https://www.mdpi.com/1424-8220/23/9/4540/pdf?version=1683529443","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:37177744","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37177744","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:10181533","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10181533","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10181533/pdf/sensors-23-04540.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:3535e98bcb4c483a90c0bdb6d840dfb8","is_oa":true,"landing_page_url":"https://doaj.org/article/3535e98bcb4c483a90c0bdb6d840dfb8","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 9, p 4540 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/23/9/4540/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s23094540","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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; Volume 23; Issue 9; Pages: 4540","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s23094540","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23094540","pdf_url":"https://www.mdpi.com/1424-8220/23/9/4540/pdf?version=1683529443","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":[{"score":0.5,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3586487095","display_name":"Construction of ultra-low-volume anonymous learning technology and universal learning technology to improve the versatility of medical AI","funder_award_id":"23K11141","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4092381066","display_name":"General-purpose deep learning theory for ultra-low computational complexity and low capacity in the age of edge AI","funder_award_id":"23K21676","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4489174082","display_name":null,"funder_award_id":"Grant JP20K19857","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G54925075","display_name":null,"funder_award_id":"JP20K19857","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8739887802","display_name":null,"funder_award_id":"JP21H03456","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4376630663.pdf"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1575206345","https://openalex.org/W1901129140","https://openalex.org/W1946152311","https://openalex.org/W1991139021","https://openalex.org/W2018541726","https://openalex.org/W2045135582","https://openalex.org/W2106414111","https://openalex.org/W2139190150","https://openalex.org/W2154091569","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2318686747","https://openalex.org/W2415148070","https://openalex.org/W2511428026","https://openalex.org/W2562637781","https://openalex.org/W2619697695","https://openalex.org/W2752782242","https://openalex.org/W2755286543","https://openalex.org/W2763188033","https://openalex.org/W2767290858","https://openalex.org/W2806238143","https://openalex.org/W2883082281","https://openalex.org/W2959214850","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W2964058413","https://openalex.org/W2982624843","https://openalex.org/W2991779680","https://openalex.org/W3034742263","https://openalex.org/W3049847664","https://openalex.org/W3095687795","https://openalex.org/W3096431533","https://openalex.org/W3108332675","https://openalex.org/W3169318522","https://openalex.org/W3174854700","https://openalex.org/W3177116139","https://openalex.org/W4289665794","https://openalex.org/W6676530657","https://openalex.org/W6761138111","https://openalex.org/W6761234640"],"related_works":["https://openalex.org/W2004108361","https://openalex.org/W2769108308","https://openalex.org/W2399778858","https://openalex.org/W2036663755","https://openalex.org/W2152217104","https://openalex.org/W2327646860","https://openalex.org/W3175554123","https://openalex.org/W2314646506","https://openalex.org/W2324103679","https://openalex.org/W2324769183"],"abstract_inverted_index":{"This":[0],"study":[1],"proposes":[2],"a":[3,57,94],"novel":[4],"off-screen":[5,75,102,111,120,149,159],"sound":[6,30,112,160],"separation":[7,163],"method":[8,72,97,117],"based":[9,39,77],"on":[10,40,78],"audio-visual":[11,17,61,68],"pre-training.":[12],"In":[13],"the":[14,101,106,115,124,140,153],"field":[15],"of":[16,123,142,155],"analysis,":[18],"researchers":[19],"have":[20,59],"leveraged":[21],"visual":[22],"information":[23],"for":[24,148],"audio":[25,35,43],"manipulation":[26,36],"tasks,":[27],"such":[28,34,74],"as":[29],"source":[31],"separation.":[32,113],"Although":[33],"tasks":[37],"are":[38,48],"correspondences":[41,47,62],"between":[42],"and":[44,63,104,162],"video,":[45],"these":[46],"not":[49],"always":[50],"established.":[51],"Specifically,":[52],"sounds":[53,76,121],"coming":[54],"from":[55,126],"outside":[56],"screen":[58],"no":[60],"thus":[64],"interfere":[65],"with":[66,88],"conventional":[67],"learning.":[69],"The":[70],"proposed":[71,116],"separates":[73],"their":[79],"arrival":[80],"directions":[81],"using":[82,134],"binaural":[83],"audio,":[84],"which":[85,127],"provides":[86],"us":[87],"three-dimensional":[89],"sensation.":[90],"Furthermore,":[91],"we":[92],"propose":[93],"new":[95],"pre-training":[96],"that":[98],"can":[99,118],"consider":[100],"space":[103],"use":[105],"obtained":[107],"representation":[108],"to":[109,138],"improve":[110],"Consequently,":[114],"separate":[119],"irrespective":[122],"direction":[125],"they":[128],"arrive.":[129],"We":[130,151],"conducted":[131],"our":[132,156],"evaluation":[133],"generated":[135],"video":[136],"data":[137],"circumvent":[139],"problem":[141],"difficulty":[143],"in":[144],"collecting":[145],"ground":[146],"truth":[147],"sounds.":[150],"confirmed":[152],"effectiveness":[154],"methods":[157],"through":[158],"detection":[161],"tasks.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}