{"id":"https://openalex.org/W4416799962","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249360","title":"Pre-training Autoencoder for Acoustic Event Classification via Blinky","display_name":"Pre-training Autoencoder for Acoustic Event Classification via Blinky","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799962","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249360"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249360","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/A5020149718","display_name":"Xiaoyang Liu","orcid":"https://orcid.org/0000-0002-5572-9080"},"institutions":[{"id":"https://openalex.org/I1314466530","display_name":"Tokai University","ror":"https://ror.org/01p7qe739","country_code":"JP","type":"education","lineage":["https://openalex.org/I1314466530"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xiaoyang Liu","raw_affiliation_strings":["Tokai University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokai University,Japan","institution_ids":["https://openalex.org/I1314466530"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043769131","display_name":"Yuma Kinoshita","orcid":"https://orcid.org/0000-0001-8455-1288"},"institutions":[{"id":"https://openalex.org/I1314466530","display_name":"Tokai University","ror":"https://ror.org/01p7qe739","country_code":"JP","type":"education","lineage":["https://openalex.org/I1314466530"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuma Kinoshita","raw_affiliation_strings":["Tokai University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokai University,Japan","institution_ids":["https://openalex.org/I1314466530"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1314466530"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38812071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"101","last_page":"106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.953000009059906,"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":0.953000009059906,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.007400000002235174,"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/T11667","display_name":"Advanced Chemical Sensor Technologies","score":0.0035000001080334187,"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/autoencoder","display_name":"Autoencoder","score":0.8220999836921692},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7275999784469604},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6654999852180481},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6341999769210815},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.47040000557899475},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46939998865127563},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4138999879360199},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.40139999985694885},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.39579999446868896}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8220999836921692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7350000143051147},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7275999784469604},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6654999852180481},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6341999769210815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6155999898910522},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5210000276565552},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.47040000557899475},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4334999918937683},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.39579999446868896},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.36890000104904175},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249360","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":[{"id":"https://openalex.org/G1127434090","display_name":null,"funder_award_id":"JP22K17915","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"}],"funders":[{"id":"https://openalex.org/F4320320212","display_name":"Japan Society for the Promotion of Science London","ror":"https://ror.org/02m7axw05"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2052666245","https://openalex.org/W2086384421","https://openalex.org/W2194775991","https://openalex.org/W2576520820","https://openalex.org/W2593116425","https://openalex.org/W2763188033","https://openalex.org/W2921870745","https://openalex.org/W3014225705","https://openalex.org/W3094550259","https://openalex.org/W3143174503","https://openalex.org/W3196974791","https://openalex.org/W3210404882","https://openalex.org/W4205962194","https://openalex.org/W4226442948","https://openalex.org/W4312069035","https://openalex.org/W4402936480","https://openalex.org/W4403182066"],"related_works":[],"abstract_inverted_index":{"In":[0,125],"the":[1,27,39,58,71,76,91,99,112,121,130,140],"acoustic":[2],"event":[3],"classification":[4],"(AEC)":[5],"framework":[6],"that":[7,56],"employs":[8],"Blinkies,":[9],"audio":[10,41],"signals":[11],"are":[12],"converted":[13],"into":[14,90],"LED":[15],"light":[16],"emissions":[17],"and":[18,43],"subsequently":[19],"captured":[20],"by":[21],"a":[22,51,61,80,126,134],"single":[23],"video":[24],"camera.":[25],"However,":[26],"30":[28],"fps":[29],"optical":[30],"transmission":[31],"channel":[32,103],"conveys":[33],"only":[34],"about":[35],"0.2":[36],"%":[37],"of":[38,60,115],"normal":[40],"bandwidth":[42,138],"is":[44,88,108],"highly":[45],"susceptible":[46],"to":[47,65],"noise.":[48,104],"We":[49],"propose":[50],"novel":[52],"sound-to-light":[53,152],"conversion":[54,153],"method":[55,142],"leverages":[57],"encoder":[59,106],"pre-trained":[62],"autoencoder":[63],"(AE)":[64],"distill":[66],"compact,":[67],"discriminative":[68],"features":[69],"from":[70],"recorded":[72],"audio.":[73],"To":[74],"pre-train":[75],"AE,":[77],"we":[78],"adopt":[79],"noiserobust":[81],"learning":[82],"strategy":[83],"in":[84],"which":[85],"artificial":[86],"noise":[87],"injected":[89],"encoder's":[92],"latent":[93],"representations":[94],"during":[95],"training,":[96],"thereby":[97],"enhancing":[98],"model's":[100],"robustness":[101],"against":[102],"The":[105],"architecture":[107],"specifically":[109],"designed":[110],"for":[111],"memory":[113],"footprint":[114],"contemporary":[116],"edge":[117],"devices":[118],"such":[119],"as":[120],"Raspberry":[122],"Pi":[123],"4.":[124],"simulation":[127],"experiment":[128],"on":[129],"ESC-50":[131],"dataset":[132],"under":[133],"stringent":[135],"15":[136],"Hz":[137],"constraint,":[139],"proposed":[141],"achieved":[143],"higher":[144],"macro-":[145],"<tex":[146],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[147],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathrm{F}_{1}$</tex>":[148],"scores":[149],"than":[150],"conventional":[151],"approaches.":[154]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}