{"id":"https://openalex.org/W4386323415","doi":"https://doi.org/10.1109/icce-taiwan58799.2023.10227056","title":"Binaural Audio Generation with Data Augmentation from 360\u00b0 Videos","display_name":"Binaural Audio Generation with Data Augmentation from 360\u00b0 Videos","publication_year":2023,"publication_date":"2023-07-17","ids":{"openalex":"https://openalex.org/W4386323415","doi":"https://doi.org/10.1109/icce-taiwan58799.2023.10227056"},"language":"en","primary_location":{"id":"doi:10.1109/icce-taiwan58799.2023.10227056","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icce-taiwan58799.2023.10227056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","raw_type":"proceedings-article"},"type":"article","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/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":true,"raw_author_name":"Masaki Yoshida","raw_affiliation_strings":["Hokkaido University,Graduate School of Information Science and Technology","Graduate School of Information Science and Technology, Hokkaido University"],"affiliations":[{"raw_affiliation_string":"Hokkaido University,Graduate School of Information Science and Technology","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, 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":["Hokkaido University,Graduate School of Information Science and Technology","Graduate School of Information Science and Technology, Hokkaido University","Faculty of Information Science and Technology, Hokkaido University"],"affiliations":[{"raw_affiliation_string":"Hokkaido University,Graduate School of Information Science and Technology","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, Hokkaido University","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, 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":["Hokkaido University,Faculty of Information Science and Technology","Faculty of Information Science and Technology, Hokkaido University"],"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology","institution_ids":["https://openalex.org/I205349734"]},{"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":["Hokkaido University,Faculty of Information Science and Technology","Faculty of Information Science and Technology, Hokkaido University"],"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology","institution_ids":["https://openalex.org/I205349734"]},{"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":4,"corresponding_author_ids":["https://openalex.org/A5006800515"],"corresponding_institution_ids":["https://openalex.org/I205349734"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1057591,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":null,"first_page":"795","last_page":"796"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9986000061035156,"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":0.9939000010490417,"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/binaural-recording","display_name":"Binaural recording","score":0.9224811792373657},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7890064716339111},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.757134199142456},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6356256008148193},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.57715904712677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33029019832611084},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32560932636260986},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06566941738128662}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.9224811792373657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7890064716339111},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.757134199142456},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6356256008148193},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.57715904712677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33029019832611084},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32560932636260986},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06566941738128662},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icce-taiwan58799.2023.10227056","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icce-taiwan58799.2023.10227056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W3034742263","https://openalex.org/W3096780661","https://openalex.org/W4200132956","https://openalex.org/W6757240503"],"related_works":["https://openalex.org/W2766995619","https://openalex.org/W4224270619","https://openalex.org/W2579722767","https://openalex.org/W2168148781","https://openalex.org/W1991848873","https://openalex.org/W2026165661","https://openalex.org/W2099651033","https://openalex.org/W2783525307","https://openalex.org/W2593008828","https://openalex.org/W2155323221"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,34],"novel":[3],"binaural":[4,16,26,78],"audio":[5,17,79,93],"generation":[6,18,54,80],"method":[7,50,71],"with":[8],"data":[9,40,53],"augmentation":[10],"from":[11,55],"360\u00b0":[12,56,84],"videos.":[13],"Visually":[14],"informed":[15],"requires":[19,33],"ground":[20,31,64],"truth":[21,32],"pairs":[22],"of":[23,36,46,63,76],"video":[24,85,90],"and":[25,38,82,91],"audio.":[27],"However,":[28],"collecting":[29],"diverse":[30],"lot":[35],"effort,":[37],"low":[39,61],"diversity":[41,62],"reduces":[42],"the":[43,47,52,60,73,77],"generalization":[44,74],"performance":[45,75],"model.":[48],"Our":[49],"introduces":[51],"videos":[57],"to":[58],"solve":[59],"truth.":[65],"Experimental":[66],"results":[67],"show":[68],"that":[69,83],"our":[70],"improves":[72],"model":[81],"is":[86],"effective":[87],"in":[88],"generating":[89],"pseudo-binaural":[92],"pairs.":[94]},"counts_by_year":[],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}
