{"id":"https://openalex.org/W4205962194","doi":"https://doi.org/10.23919/eusipco54536.2021.9616341","title":"End-to-End Training for Acoustic Scene Analysis with Distributed Sound-to-Light Conversion Devices","display_name":"End-to-End Training for Acoustic Scene Analysis with Distributed Sound-to-Light Conversion Devices","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W4205962194","doi":"https://doi.org/10.23919/eusipco54536.2021.9616341"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616341","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616341","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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 29th European Signal Processing Conference (EUSIPCO)","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/A5043769131","display_name":"Yuma Kinoshita","orcid":"https://orcid.org/0000-0001-8455-1288"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuma Kinoshita","raw_affiliation_strings":["Tokyo Metropolitan University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University, Tokyo, Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056281759","display_name":"Nobutaka Ono","orcid":"https://orcid.org/0000-0003-4242-2773"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobutaka Ono","raw_affiliation_strings":["Tokyo Metropolitan University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University, Tokyo, Japan","institution_ids":["https://openalex.org/I69740276"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043769131"],"corresponding_institution_ids":["https://openalex.org/I69740276"],"apc_list":null,"apc_paid":null,"fwci":0.6881,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74076561,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1010","last_page":"1014"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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":0.9987999796867371,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9961000084877014,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9916999936103821,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7531662583351135},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.5228217840194702},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4740338623523712},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.47319695353507996},{"id":"https://openalex.org/keywords/attenuation","display_name":"Attenuation","score":0.4730127155780792},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.4411441683769226},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.419073224067688},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4109795093536377},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3652194142341614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3584054708480835},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.28883957862854004},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.20301753282546997},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.12895429134368896},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12414407730102539}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7531662583351135},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5228217840194702},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4740338623523712},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.47319695353507996},{"id":"https://openalex.org/C184652730","wikidata":"https://www.wikidata.org/wiki/Q2357982","display_name":"Attenuation","level":2,"score":0.4730127155780792},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.4411441683769226},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.419073224067688},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4109795093536377},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3652194142341614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3584054708480835},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.28883957862854004},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.20301753282546997},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.12895429134368896},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12414407730102539},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616341","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616341","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3135745873","display_name":null,"funder_award_id":"JP20H00613","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5000949750","display_name":null,"funder_award_id":"JPMJCR19A3","funder_id":"https://openalex.org/F4320320907","funder_display_name":"Japan Science and Technology Corporation"}],"funders":[{"id":"https://openalex.org/F4320320907","display_name":"Japan Science and Technology Corporation","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W1901129140","https://openalex.org/W2008415856","https://openalex.org/W2103235956","https://openalex.org/W2105068979","https://openalex.org/W2220333611","https://openalex.org/W2576520820","https://openalex.org/W2618657287","https://openalex.org/W2921870745","https://openalex.org/W2925717635","https://openalex.org/W2963452667","https://openalex.org/W2987090363","https://openalex.org/W3014225705","https://openalex.org/W3036237438","https://openalex.org/W4394023065","https://openalex.org/W6637373629","https://openalex.org/W6639824700","https://openalex.org/W6652556484","https://openalex.org/W6751512325","https://openalex.org/W6779574021"],"related_works":["https://openalex.org/W2062605435","https://openalex.org/W2273182195","https://openalex.org/W2186374051","https://openalex.org/W2377963109","https://openalex.org/W2022279172","https://openalex.org/W2352247021","https://openalex.org/W2059332403","https://openalex.org/W2977517636","https://openalex.org/W1969179582","https://openalex.org/W2810129309"],"abstract_inverted_index":{"We":[0,68,104],"propose":[1],"an":[2,23,131],"end-to-end":[3,132],"acoustic":[4,35,77,127,137,169],"scene":[5,78,128,138,170],"analysis":[6,79,129,139],"framework":[7,149,158],"with":[8,159],"distributed":[9,45],"sound-to-light":[10,73,124],"conversion":[11,74,125],"devices":[12],"called":[13],"Blinkies.":[14,160],"Blinkies":[15,44,167],"transmit":[16],"sound":[17],"information":[18,36],"as":[19,96,109],"the":[20,39,51,72,106,147,156,164],"intensity":[21],"of":[22,136,166],"on-board":[24],"light-emitting":[25],"diode":[26],"(LED).":[27],"A":[28],"video":[29,59],"camera":[30],"can":[31,150],"then":[32],"easily":[33],"collect":[34],"by":[37],"capturing":[38],"LED":[40],"intensities":[41],"from":[42],"multiple":[43],"over":[46],"a":[47,58,141,152],"large":[48],"area.":[49],"However,":[50],"transmitted":[52],"signal":[53,89],"is":[54],"band-limited":[55],"owing":[56],"to":[57,70,92,116],"camera's":[60],"frame":[61],"rate,":[62],"typically":[63],"30":[64],"frames":[65],"per":[66],"second.":[67],"aim":[69],"optimize":[71],"process":[75],"for":[76,123,168],"under":[80],"this":[81],"bandwidth":[82],"constraint.":[83],"In":[84],"light-signal":[85],"propagation":[86],"in":[87,130],"air,":[88],"degradation":[90],"due":[91],"physical":[93,107,111],"constraints":[94,108],"such":[95],"light":[97],"attenuation":[98],"and":[99,126],"noise":[100],"will":[101],"also":[102],"occur.":[103],"model":[105],"differentiable":[110],"layers,":[112],"which":[113],"enable":[114],"us":[115],"train":[117],"two":[118],"deep":[119],"neural":[120],"networks":[121],"(DNNs)":[122],"manner.":[133],"Simulation":[134],"experiments":[135],"using":[140],"DCASE":[142],"2018":[143],"dataset":[144],"show":[145],"that":[146],"proposed":[148],"produce":[151],"higher":[153],"accuracy":[154],"than":[155],"previous":[157],"This":[161],"result":[162],"suggests":[163],"suitability":[165],"analysis.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}