{"id":"https://openalex.org/W4406860192","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848791","title":"Integrating VGGSK and BEATs for Enhanced Sound Event Detection: A Semi-Supervised GRU-Based System with Weak Labels and Synthetic Soundscapes","display_name":"Integrating VGGSK and BEATs for Enhanced Sound Event Detection: A Semi-Supervised GRU-Based System with Weak Labels and Synthetic Soundscapes","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406860192","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848791"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5051255494","display_name":"Paul K.S. Chan","orcid":"https://orcid.org/0000-0002-6360-4608"},"institutions":[{"id":"https://openalex.org/I92172085","display_name":"Chunghwa Telecom (Taiwan)","ror":"https://ror.org/04f786589","country_code":"TW","type":"company","lineage":["https://openalex.org/I92172085"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Po Cheng Chan","raw_affiliation_strings":["Chunghwa Telecom Laboratories,Advanced Technology Laboratory,Taoyuan,Taiwan"],"affiliations":[{"raw_affiliation_string":"Chunghwa Telecom Laboratories,Advanced Technology Laboratory,Taoyuan,Taiwan","institution_ids":["https://openalex.org/I92172085"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373297","display_name":"Wei-Yu Chen","orcid":"https://orcid.org/0000-0001-7355-9188"},"institutions":[{"id":"https://openalex.org/I92172085","display_name":"Chunghwa Telecom (Taiwan)","ror":"https://ror.org/04f786589","country_code":"TW","type":"company","lineage":["https://openalex.org/I92172085"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Yu Chen","raw_affiliation_strings":["Chunghwa Telecom Laboratories,Advanced Technology Laboratory,Taoyuan,Taiwan"],"affiliations":[{"raw_affiliation_string":"Chunghwa Telecom Laboratories,Advanced Technology Laboratory,Taoyuan,Taiwan","institution_ids":["https://openalex.org/I92172085"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120312101","display_name":"Chunyan Lu","orcid":"https://orcid.org/0000-0001-7046-6154"},"institutions":[{"id":"https://openalex.org/I92172085","display_name":"Chunghwa Telecom (Taiwan)","ror":"https://ror.org/04f786589","country_code":"TW","type":"company","lineage":["https://openalex.org/I92172085"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung Li Lu","raw_affiliation_strings":["Chunghwa Telecom Laboratories,Advanced Technology Laboratory,Taoyuan,Taiwan"],"affiliations":[{"raw_affiliation_string":"Chunghwa Telecom Laboratories,Advanced Technology Laboratory,Taoyuan,Taiwan","institution_ids":["https://openalex.org/I92172085"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113361561","display_name":"Hsiang-Feng Chuang","orcid":null},"institutions":[{"id":"https://openalex.org/I92172085","display_name":"Chunghwa Telecom (Taiwan)","ror":"https://ror.org/04f786589","country_code":"TW","type":"company","lineage":["https://openalex.org/I92172085"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsiang-Feng Chuang","raw_affiliation_strings":["Chunghwa Telecom Laboratories,Advanced Technology Laboratory,Taoyuan,Taiwan"],"affiliations":[{"raw_affiliation_string":"Chunghwa Telecom Laboratories,Advanced Technology Laboratory,Taoyuan,Taiwan","institution_ids":["https://openalex.org/I92172085"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101269022","display_name":"Yu-Han Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I92172085","display_name":"Chunghwa Telecom (Taiwan)","ror":"https://ror.org/04f786589","country_code":"TW","type":"company","lineage":["https://openalex.org/I92172085"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Han Cheng","raw_affiliation_strings":["Chunghwa Telecom Laboratories,Advanced Technology Laboratory,Taoyuan,Taiwan"],"affiliations":[{"raw_affiliation_string":"Chunghwa Telecom Laboratories,Advanced Technology Laboratory,Taoyuan,Taiwan","institution_ids":["https://openalex.org/I92172085"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029325015","display_name":"Jia\u2010Ching Wang","orcid":"https://orcid.org/0000-0003-0024-6732"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jia Ching Wang","raw_affiliation_strings":["National Central University,Department of Computer Science and Information Engineering"],"affiliations":[{"raw_affiliation_string":"National Central University,Department of Computer Science and Information Engineering","institution_ids":["https://openalex.org/I22265921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5051255494"],"corresponding_institution_ids":["https://openalex.org/I92172085"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30149382,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.9984999895095825,"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":0.988099992275238,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9509999752044678,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/soundscape","display_name":"Soundscape","score":0.846139669418335},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6390794515609741},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6318246126174927},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5423226952552795},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.45412296056747437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4180281162261963},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.35027509927749634},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07989716529846191}],"concepts":[{"id":"https://openalex.org/C142795923","wikidata":"https://www.wikidata.org/wiki/Q1358257","display_name":"Soundscape","level":3,"score":0.846139669418335},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6390794515609741},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6318246126174927},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5423226952552795},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.45412296056747437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4180281162261963},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.35027509927749634},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07989716529846191},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10848791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2922509574","https://openalex.org/W2950635152","https://openalex.org/W2959539607","https://openalex.org/W3209458476","https://openalex.org/W4224920041","https://openalex.org/W4307823382","https://openalex.org/W6637373629","https://openalex.org/W6733814495","https://openalex.org/W6848208918"],"related_works":["https://openalex.org/W1254698036","https://openalex.org/W2896201871","https://openalex.org/W1988083194","https://openalex.org/W2282503792","https://openalex.org/W2970126706","https://openalex.org/W2365709658","https://openalex.org/W2747085439","https://openalex.org/W1562588264","https://openalex.org/W1593731728","https://openalex.org/W2770198033"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,8,69,82,89,131],"architecture":[4],"we":[5,67,97],"developed":[6],"for":[7,124,128],"Detection":[9,26,119],"and":[10,15,30,38,40,57,106,126],"Classification":[11],"of":[12,122],"Acoustic":[13],"Scenes":[14],"Events":[16],"(DCASE)":[17],"2023":[18],"Challenge,":[19],"specifically":[20],"Task":[21],"4":[22],"on":[23,130],"Sound":[24,118],"Event":[25],"using":[27],"Weak":[28],"Labels":[29],"Synthetic":[31],"Soundscapes.":[32],"We":[33],"integrated":[34],"embeddings":[35],"from":[36],"VGGSK":[37],"BEATs,":[39],"employed":[41],"a":[42,116],"GRU-based":[43],"model":[44],"to":[45,80],"classify":[46],"sound":[47],"events":[48],"in":[49,60],"each":[50],"time":[51],"frame.":[52],"The":[53],"system":[54,114],"employs":[55],"thresholding":[56],"smoothing":[58],"techniques":[59],"its":[61],"post-processing":[62],"phase.":[63],"For":[64],"semi-supervised":[65],"learning,":[66],"used":[68],"mean":[70],"teacher":[71,83],"approach":[72],"with":[73],"an":[74],"Exponential":[75],"Moving":[76],"Average":[77],"(EMA)":[78],"strategy":[79],"update":[81],"model\u2019s":[84],"parameters.":[85],"Pseudo-labels,":[86],"generated":[87],"by":[88],"student":[90],"model,":[91],"help":[92],"leverage":[93],"unlabeled":[94],"data.":[95],"Additionally,":[96],"applied":[98],"data":[99],"augmentation":[100],"methods":[101],"including":[102],"mix-up,":[103],"Gaussian":[104],"noise,":[105],"embedding":[107],"masking.":[108],"With":[109],"additional":[110],"training":[111],"data,":[112],"our":[113],"achieved":[115],"Polyphonic":[117],"Score":[120],"(PSDS)":[121],"0.529":[123],"PSDS1":[125],"0.78":[127],"PSDS2":[129],"validation":[132],"dataset.":[133]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
