{"id":"https://openalex.org/W4312909419","doi":"https://doi.org/10.1007/978-3-031-19836-6_21","title":"AudioScopeV2: Audio-Visual Attention Architectures for\u00a0Calibrated Open-Domain On-Screen Sound Separation","display_name":"AudioScopeV2: Audio-Visual Attention Architectures for\u00a0Calibrated Open-Domain On-Screen Sound Separation","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4312909419","doi":"https://doi.org/10.1007/978-3-031-19836-6_21"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-19836-6_21","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-19836-6_21","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"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/A5016864112","display_name":"Efthymios Tzinis","orcid":"https://orcid.org/0000-0002-1047-1338"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Efthymios Tzinis","raw_affiliation_strings":["Google Research, Cambridge, USA","University of Illinois Urbana-Champaign, Urbana, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053447215","display_name":"Scott Wisdom","orcid":"https://orcid.org/0000-0001-6671-1428"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Wisdom","raw_affiliation_strings":["Google Research, Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015117736","display_name":"Tal Remez","orcid":"https://orcid.org/0000-0002-9930-8624"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tal Remez","raw_affiliation_strings":["Google Research, Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Google Research, Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"368","last_page":"385"},"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":0.9997000098228455,"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":0.9965000152587891,"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":0.8814729452133179},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5448900461196899},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5353947281837463},{"id":"https://openalex.org/keywords/surround-sound","display_name":"Surround sound","score":0.4579007625579834},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4343399405479431},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42509356141090393},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.3181743323802948},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24253925681114197},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.15334856510162354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8814729452133179},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5448900461196899},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5353947281837463},{"id":"https://openalex.org/C2780544925","wikidata":"https://www.wikidata.org/wiki/Q569874","display_name":"Surround sound","level":3,"score":0.4579007625579834},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4343399405479431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42509356141090393},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.3181743323802948},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24253925681114197},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.15334856510162354},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-19836-6_21","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-19836-6_21","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2250384498","https://openalex.org/W2593116425","https://openalex.org/W2899515918","https://openalex.org/W2933708090","https://openalex.org/W2962699416","https://openalex.org/W2962960500","https://openalex.org/W2963115079","https://openalex.org/W2963189033","https://openalex.org/W2963218389","https://openalex.org/W2964058413","https://openalex.org/W2964171275","https://openalex.org/W2964237233","https://openalex.org/W2973062255","https://openalex.org/W2981436548","https://openalex.org/W2988200020","https://openalex.org/W2990113535","https://openalex.org/W2990666817","https://openalex.org/W2998657200","https://openalex.org/W3015817524","https://openalex.org/W3017343282","https://openalex.org/W3048939150","https://openalex.org/W3095263845","https://openalex.org/W3096431533","https://openalex.org/W3099638501","https://openalex.org/W3116298410","https://openalex.org/W3154852953","https://openalex.org/W3160972914","https://openalex.org/W3170717896","https://openalex.org/W3172237229","https://openalex.org/W3173382920","https://openalex.org/W3182657421","https://openalex.org/W4214497471","https://openalex.org/W4214516465","https://openalex.org/W4224871700","https://openalex.org/W4289665794","https://openalex.org/W4297841626","https://openalex.org/W6600157417","https://openalex.org/W6828894009"],"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/W1984634519","https://openalex.org/W2912980217"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}