{"id":"https://openalex.org/W2800288142","doi":"https://doi.org/10.1145/3197517.3201391","title":"Scene-aware audio for 360\u00b0 videos","display_name":"Scene-aware audio for 360\u00b0 videos","publication_year":2018,"publication_date":"2018-07-30","ids":{"openalex":"https://openalex.org/W2800288142","doi":"https://doi.org/10.1145/3197517.3201391","mag":"2800288142"},"language":"en","primary_location":{"id":"doi:10.1145/3197517.3201391","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3197517.3201391","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1805.04792","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Dingzeyu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dingzeyu Li","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Timothy R. Langlois","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Timothy R. Langlois","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":null,"display_name":"Changxi Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changxi Zheng","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":2.8208,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.9170528,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"37","issue":"4","first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.67330002784729,"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":0.67330002784729,"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":0.15919999778270721,"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.02070000022649765,"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/reverberation","display_name":"Reverberation","score":0.9476000070571899},{"id":"https://openalex.org/keywords/ambisonics","display_name":"Ambisonics","score":0.7914999723434448},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7441999912261963},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.6539999842643738},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.6205999851226807},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.492000013589859}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.9476000070571899},{"id":"https://openalex.org/C47726159","wikidata":"https://www.wikidata.org/wiki/Q457547","display_name":"Ambisonics","level":3,"score":0.7914999723434448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573000192642212},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7441999912261963},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.6539999842643738},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.6205999851226807},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5878000259399414},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.492000013589859},{"id":"https://openalex.org/C2776009117","wikidata":"https://www.wikidata.org/wiki/Q2305951","display_name":"Architectural acoustics","level":3,"score":0.4142000079154968},{"id":"https://openalex.org/C178432105","wikidata":"https://www.wikidata.org/wiki/Q2182127","display_name":"Room acoustics","level":3,"score":0.4083999991416931},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3635999858379364},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.31209999322891235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3082999885082245},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29840001463890076},{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.2808000147342682},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.27079999446868896}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3197517.3201391","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3197517.3201391","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1805.04792","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.04792","pdf_url":"https://arxiv.org/pdf/1805.04792","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1805.04792","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.04792","pdf_url":"https://arxiv.org/pdf/1805.04792","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1532179378","https://openalex.org/W1559975096","https://openalex.org/W1964603069","https://openalex.org/W2001918695","https://openalex.org/W2005126631","https://openalex.org/W2012579141","https://openalex.org/W2015939683","https://openalex.org/W2058733260","https://openalex.org/W2093632550","https://openalex.org/W2099332139","https://openalex.org/W2101038365","https://openalex.org/W2112261915","https://openalex.org/W2144313611","https://openalex.org/W2302108082","https://openalex.org/W2408467190","https://openalex.org/W2472178346","https://openalex.org/W2531849700","https://openalex.org/W2551677029","https://openalex.org/W2555915854","https://openalex.org/W2556362500","https://openalex.org/W2604941723","https://openalex.org/W2605221279","https://openalex.org/W2737697117","https://openalex.org/W2738549586","https://openalex.org/W4234232628"],"related_works":[],"abstract_inverted_index":{"Although":[0],"360\u00b0":[1,15,40],"cameras":[2],"ease":[3],"the":[4,20,27,58,81,145,149,172],"capture":[5,123],"of":[6,61,174],"panoramic":[7],"footage,":[8],"it":[9],"remains":[10],"challenging":[11],"to":[12,39,122],"add":[13],"realistic":[14],"audio":[16,38,161],"that":[17,57,79,142,157],"blends":[18],"into":[19],"captured":[21],"scene":[22],"and":[23,52,70,88,98,114],"is":[24,66,107,129],"synchronized":[25],"with":[26,136,164],"camera":[28],"motion.":[29],"We":[30,55],"present":[31],"a":[32,48,53,62,77,93,99,110,118,132,137],"method":[33,78,121,176],"for":[34],"adding":[35],"scene-aware":[36],"spatial":[37,160],"videos":[41],"in":[42,177],"typical":[43],"indoor":[44],"scenes,":[45],"using":[46,109,117,166],"only":[47],"conventional":[49],"mono-channel":[50],"microphone":[51],"speaker.":[54],"observe":[56],"late":[59,101,127,146],"reverberation":[60,96,102,106,128,147],"room's":[63],"impulse":[64,83,134],"response":[65,84],"usually":[67],"diffuse":[68],"spatially":[69],"directionally.":[71],"Exploiting":[72],"this":[73],"fact,":[74],"we":[75,155,170],"propose":[76],"synthesizes":[80],"directional":[82],"between":[85],"any":[86],"source":[87],"listening":[89],"locations":[90],"by":[91],"combining":[92],"synthesized":[94,159],"early":[95,105,150],"part":[97],"measured":[100],"tail.":[103],"The":[104,126],"simulated":[108],"geometric":[111],"acoustic":[112],"simulation":[113],"then":[115],"enhanced":[116],"frequency":[119],"modulation":[120],"room":[124],"resonances.":[125],"extracted":[130],"from":[131,148],"recorded":[133],"response,":[135],"carefully":[138],"chosen":[139],"time":[140],"duration":[141],"separates":[143],"out":[144],"reverberation.":[151],"In":[152],"our":[153,158,175],"validations,":[154],"show":[156],"matches":[162],"closely":[163],"recordings":[165],"ambisonic":[167],"microphones.":[168],"Lastly,":[169],"demonstrate":[171],"strength":[173],"several":[178],"applications.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2018-05-17T00:00:00"}
