{"id":"https://openalex.org/W4416799316","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249225","title":"First Demonstration of Acoustic Scene Classification Based on Trained Sound-to-Light Conversion","display_name":"First Demonstration of Acoustic Scene Classification Based on Trained Sound-to-Light Conversion","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799316","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249225"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5120525835","display_name":"Shun Kotsugi","orcid":null},"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":"Shun Kotsugi","raw_affiliation_strings":["Tokyo Metropolitan University,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University,Tokyo,Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050509317","display_name":"Takao Kawamura","orcid":"https://orcid.org/0009-0005-3935-2809"},"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":"Takao Kawamura","raw_affiliation_strings":["Tokyo Metropolitan University,Tokyo,Japan"],"raw_orcid":null,"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University,Tokyo,Japan","institution_ids":["https://openalex.org/I69740276"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I69740276"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40416802,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"48","last_page":"53"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.35580000281333923,"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/T11309","display_name":"Music and Audio Processing","score":0.35580000281333923,"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/T10860","display_name":"Speech and Audio Processing","score":0.2393999993801117,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.04320000112056732,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.47350001335144043},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39910000562667847},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.3871000111103058},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.34769999980926514},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.29339998960494995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7171000242233276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5814999938011169},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.47350001335144043},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46140000224113464},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4108000099658966},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2903999984264374},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":18,"referenced_works":["https://openalex.org/W2092463830","https://openalex.org/W2127639136","https://openalex.org/W2160860215","https://openalex.org/W2166595512","https://openalex.org/W2618657287","https://openalex.org/W2801393360","https://openalex.org/W2970903410","https://openalex.org/W2982697612","https://openalex.org/W3014225705","https://openalex.org/W4221155627","https://openalex.org/W4285376717","https://openalex.org/W4311186284","https://openalex.org/W4312069035","https://openalex.org/W4312097123","https://openalex.org/W4386918931","https://openalex.org/W4387244556","https://openalex.org/W4392114354","https://openalex.org/W4402936480"],"related_works":[],"abstract_inverted_index":{"In":[0,29],"this":[1,30],"paper,":[2],"we":[3,32,63],"present":[4],"the":[5,56,77,101,122],"first":[6],"experimental":[7],"demonstration":[8],"of":[9,59,124,140],"acoustic":[10,24,41],"scene":[11],"classification":[12,74],"(ASC)":[13],"using":[14,68,76,110,126],"trained":[15,102,127],"sound-to-light":[16,53,128],"conversion":[17,54,103,129],"with":[18],"Blinkies,":[19],"compact":[20],"devices":[21],"that":[22,88],"convert":[23],"signals":[25,44,71,113],"into":[26],"optical":[27,43,112],"signals.":[28],"study,":[31],"construct":[33],"a":[34,46,116,135],"small-scale":[35],"real-world":[36],"dataset":[37],"by":[38,115],"recording":[39],"both":[40],"and":[42,72,106,133,144],"in":[45,83,130],"simulated":[47],"living":[48],"environment.":[49],"To":[50],"realize":[51],"effective":[52],"under":[55],"bandwidth":[57],"limitations":[58],"standard":[60],"video":[61,117],"cameras,":[62],"train":[64],"frequency":[65],"subband":[66],"weights":[67],"recorded":[69],"audio":[70],"evaluate":[73],"performance":[75],"resulting":[78],"filtered":[79],"short-time":[80],"power":[81],"features":[82,90],"simulation.":[84],"The":[85],"results":[86,120],"show":[87],"these":[89],"achieve":[91],"accuracy":[92],"comparable":[93],"to":[94],"conventional":[95],"spectral":[96],"features.":[97],"We":[98],"then":[99],"implement":[100],"on":[104],"Blinkies":[105],"successfully":[107],"perform":[108],"ASC":[109,125],"actual":[111],"captured":[114],"camera.":[118],"These":[119],"demonstrate":[121],"feasibility":[123],"real":[131],"environments":[132],"provide":[134],"foundation":[136],"for":[137],"future":[138],"development":[139],"Blinky-based":[141],"sensing":[142],"systems":[143],"datasets.":[145]},"counts_by_year":[],"updated_date":"2026-07-05T07:55:05.734416","created_date":"2025-11-28T00:00:00"}