{"id":"https://openalex.org/W4372260405","doi":"https://doi.org/10.1109/icassp49357.2023.10096349","title":"Binauralization Robust To Camera Rotation Using 360\u00b0 Videos","display_name":"Binauralization Robust To Camera Rotation Using 360\u00b0 Videos","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260405","doi":"https://doi.org/10.1109/icassp49357.2023.10096349"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096349","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":["Hokkaido University,Faculty of Information Science and Technology,Japan","Faculty of Information Science and Technology, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, 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":["Hokkaido University,Faculty of Information Science and Technology,Japan","Faculty of Information Science and Technology, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, 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":["Hokkaido University,Faculty of Information Science and Technology,Japan","Faculty of Information Science and Technology, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, Japan","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":["Hokkaido University,Faculty of Information Science and Technology,Japan","Faculty of Information Science and Technology, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, 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":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9979000091552734,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.817784309387207},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.737883448600769},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7370396852493286},{"id":"https://openalex.org/keywords/rotation","display_name":"Rotation (mathematics)","score":0.6326937675476074},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.5889137983322144},{"id":"https://openalex.org/keywords/camera-auto-calibration","display_name":"Camera auto-calibration","score":0.5342444777488708},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4312964677810669},{"id":"https://openalex.org/keywords/single-camera","display_name":"Single camera","score":0.42636919021606445},{"id":"https://openalex.org/keywords/camera-resectioning","display_name":"Camera resectioning","score":0.23392927646636963},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.18504378199577332}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817784309387207},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.737883448600769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7370396852493286},{"id":"https://openalex.org/C74050887","wikidata":"https://www.wikidata.org/wiki/Q848368","display_name":"Rotation (mathematics)","level":2,"score":0.6326937675476074},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.5889137983322144},{"id":"https://openalex.org/C94816000","wikidata":"https://www.wikidata.org/wiki/Q5026006","display_name":"Camera auto-calibration","level":3,"score":0.5342444777488708},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4312964677810669},{"id":"https://openalex.org/C3018868555","wikidata":"https://www.wikidata.org/wiki/Q2918907","display_name":"Single camera","level":2,"score":0.42636919021606445},{"id":"https://openalex.org/C110898773","wikidata":"https://www.wikidata.org/wiki/Q2933935","display_name":"Camera resectioning","level":2,"score":0.23392927646636963},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.18504378199577332},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096349","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":31,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1901129140","https://openalex.org/W2018541726","https://openalex.org/W2028857061","https://openalex.org/W2049193094","https://openalex.org/W2053562333","https://openalex.org/W2106414111","https://openalex.org/W2120847449","https://openalex.org/W2133564696","https://openalex.org/W2139515761","https://openalex.org/W2139859857","https://openalex.org/W2194775991","https://openalex.org/W2318686747","https://openalex.org/W2767382284","https://openalex.org/W2809453856","https://openalex.org/W2963095856","https://openalex.org/W2982624843","https://openalex.org/W2997032998","https://openalex.org/W3034742263","https://openalex.org/W3096780661","https://openalex.org/W3108332675","https://openalex.org/W3138953166","https://openalex.org/W3174854700","https://openalex.org/W3205786327","https://openalex.org/W4205278059","https://openalex.org/W4286851395","https://openalex.org/W6630875275","https://openalex.org/W6639824700","https://openalex.org/W6679434410","https://openalex.org/W6792340124","https://openalex.org/W6800534558"],"related_works":["https://openalex.org/W2521915339","https://openalex.org/W2134428839","https://openalex.org/W4360877334","https://openalex.org/W2362994467","https://openalex.org/W2786586521","https://openalex.org/W1808721984","https://openalex.org/W2163971041","https://openalex.org/W2726050554","https://openalex.org/W1766145188","https://openalex.org/W2110847202"],"abstract_inverted_index":{"We":[0,110],"propose":[1,99],"a":[2,17,62,100,132],"novel":[3],"binauralization":[4,56,133,162],"method":[5,158],"that":[6,135,156],"is":[7],"robust":[8],"to":[9,20,42,66,74,82],"camera":[10,67,118,140,143,147,166],"rotation.":[11,68,167],"Since":[12],"binaural":[13,36,115],"audio":[14,37,41,116],"can":[15,24,60,159],"bring":[16],"3D":[18],"sensation":[19],"the":[21,26,30,44,76,83,86,90,124,146,151,161],"listener,":[22],"it":[23,72],"enhance":[25],"immersive":[27],"experience":[28,45],"of":[29,46,85,126],"video.":[31],"Researchers":[32],"have":[33],"been":[34],"explored":[35],"generation":[38,103],"from":[39,120],"monaural":[40],"deepen":[43],"already":[47],"captured":[48],"videos":[49,59,107,113,122,164],"without":[50],"special":[51],"recording":[52],"devices.":[53],"However,":[54],"this":[55,96],"on":[57,163],"real-world":[58],"be":[61],"challenging":[63],"task":[64],"due":[65,81],"Camera":[69],"rotation":[70,119,148],"makes":[71],"difficult":[73],"predict":[75],"exact":[77],"sound":[78,87],"source":[79],"position":[80],"motion":[84],"sources":[88],"and":[89,114,149],"background":[91],"in":[92],"videos.":[93],"To":[94],"tackle":[95],"problem,":[97],"we":[98,129],"training":[101,125],"data":[102],"pipeline":[104],"using":[105],"360\u00b0":[106,121],"for":[108,123],"binauralization.":[109,127,152],"generate":[111],"monocular":[112],"with":[117,139,165],"Additionally,":[128],"newly":[130],"construct":[131],"framework":[134],"conducts":[136],"multi-task":[137],"learning":[138],"localization.":[141],"The":[142],"localization":[144],"predicts":[145],"helps":[150],"Experimental":[153],"results":[154],"show":[155],"our":[157],"achieve":[160]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}