{"id":"https://openalex.org/W4200132956","doi":"https://doi.org/10.1109/gcce53005.2021.9621901","title":"Detection of Off-screen Sound Based on Loss Function of Self-supervised Audio-visual Spatialization","display_name":"Detection of Off-screen Sound Based on Loss Function of Self-supervised Audio-visual Spatialization","publication_year":2021,"publication_date":"2021-10-12","ids":{"openalex":"https://openalex.org/W4200132956","doi":"https://doi.org/10.1109/gcce53005.2021.9621901"},"language":"en","primary_location":{"id":"doi:10.1109/gcce53005.2021.9621901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce53005.2021.9621901","pdf_url":null,"source":{"id":"https://openalex.org/S4363607807","display_name":"2021 IEEE 10th Global Conference on Consumer Electronics (GCCE)","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":"2021 IEEE 10th Global Conference on Consumer Electronics (GCCE)","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/A5088408014","display_name":"Masaki Yoshida","orcid":"https://orcid.org/0000-0002-4744-2805"},"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":["School of Engineering, Hokkaido University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Hokkaido University","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":["Education and Research Center for Mathematical and Data Science, Hokkaido University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Education and Research Center for Mathematical and Data Science, Hokkaido University","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":null,"display_name":"Miki Haseyama","orcid":null},"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":"Miki Haseyama","raw_affiliation_strings":["Faculty of Information Science and Technology, Hokkaido University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University","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":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"193","last_page":"194"},"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":0.9927999973297119,"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/spatialization","display_name":"Spatialization","score":0.9784941673278809},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7892221212387085},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7160782217979431},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5888976454734802},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5661522746086121},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5296596884727478},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5271453857421875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5026476383209229},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4531429708003998},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43920961022377014},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.43783241510391235},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.41964611411094666},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1821562945842743},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.15253615379333496},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14763495326042175},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07560306787490845}],"concepts":[{"id":"https://openalex.org/C2777031145","wikidata":"https://www.wikidata.org/wiki/Q4430987","display_name":"Spatialization","level":2,"score":0.9784941673278809},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7892221212387085},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7160782217979431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5888976454734802},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5661522746086121},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5296596884727478},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5271453857421875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5026476383209229},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4531429708003998},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43920961022377014},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.43783241510391235},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.41964611411094666},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1821562945842743},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.15253615379333496},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14763495326042175},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07560306787490845},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcce53005.2021.9621901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce53005.2021.9621901","pdf_url":null,"source":{"id":"https://openalex.org/S4363607807","display_name":"2021 IEEE 10th Global Conference on Consumer Electronics (GCCE)","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":"2021 IEEE 10th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2750143381","https://openalex.org/W2962960500","https://openalex.org/W3017343282","https://openalex.org/W3096780661","https://openalex.org/W6637373629","https://openalex.org/W6743691625","https://openalex.org/W6757240503"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W2336774810","https://openalex.org/W3132176577","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W2114974607","https://openalex.org/W4315836293","https://openalex.org/W3112881379","https://openalex.org/W2002298560","https://openalex.org/W2019256813"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,11,22,49],"method":[4,75,116],"to":[5],"detect":[6],"off-screen":[7,78,125],"sounds":[8,64,79,85],"based":[9],"on":[10,82],"loss":[12],"function":[13],"of":[14,36,124],"self-supervised":[15],"audio-visual":[16,26,98],"spatialization.":[17],"Audio":[18],"source":[19,27,56],"separation":[20,28],"is":[21],"long-standing":[23],"problem,":[24],"and":[25,42,86],"has":[29,51],"recently":[30],"attracted":[31],"attention":[32],"in":[33,48,70,89,121],"the":[34,71,90,94,114,122],"field":[35],"acoustic":[37],"signal":[38],"processing,":[39],"image":[40],"processing":[41],"machine":[43],"learning.":[44],"Although":[45],"visual":[46,108],"information":[47,62],"video":[50],"important":[52],"cues":[53],"for":[54],"audio":[55,103,106],"separation,":[57],"it":[58],"does":[59],"not":[60,68],"have":[61],"about":[63],"whose":[65],"sources":[66,88],"are":[67],"found":[69],"video.":[72,91],"The":[73],"proposed":[74,115],"detects":[76],"such":[77],"by":[80],"focusing":[81],"correspondences":[83],"between":[84],"their":[87],"For":[92],"finding":[93],"correspondences,":[95],"we":[96],"use":[97],"spatialization,":[99],"which":[100],"converts":[101],"mono":[102],"into":[104],"spatial":[105],"with":[107],"guidance.":[109],"Experimental":[110],"results":[111],"show":[112],"that":[113],"can":[117],"achieve":[118],"high":[119],"accuracy":[120],"task":[123],"sound":[126],"detection.":[127]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
