{"id":"https://openalex.org/W4406858459","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848691","title":"Prediction-error-based Adaptive SpecAugment for Fine-tuning the Masked Model on Audio Classification Tasks","display_name":"Prediction-error-based Adaptive SpecAugment for Fine-tuning the Masked Model on Audio Classification Tasks","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858459","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848691"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848691","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/A5100752953","display_name":"Xiao Zhang","orcid":"https://orcid.org/0000-0002-5162-5962"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xiao Zhang","raw_affiliation_strings":["Waseda University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101265449","display_name":"Haoran Xing","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haoran Xing","raw_affiliation_strings":["Waseda University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113336034","display_name":"Mingxue Song","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mingxue Song","raw_affiliation_strings":["Waseda University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103978078","display_name":"Daiki Takeuchi","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daiki Takeuchi","raw_affiliation_strings":["NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054467679","display_name":"Noboru Harada","orcid":"https://orcid.org/0000-0002-1759-4533"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Noboru Harada","raw_affiliation_strings":["NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075702573","display_name":"Shoji Makino","orcid":"https://orcid.org/0000-0003-1934-640X"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoji Makino","raw_affiliation_strings":["Waseda University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6114,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69055064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9674000144004822,"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":0.9674000144004822,"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":0.9000999927520752,"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":0.7588014602661133},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6123343110084534},{"id":"https://openalex.org/keywords/mean-squared-prediction-error","display_name":"Mean squared prediction error","score":0.5598226189613342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4711821377277374},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.47023293375968933},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37029099464416504},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.30666840076446533}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7588014602661133},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6123343110084534},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.5598226189613342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4711821377277374},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.47023293375968933},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37029099464416504},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30666840076446533},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/apsipaasc63619.2025.10848691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848691","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":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1972567154","https://openalex.org/W2052666245","https://openalex.org/W2131981197","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2787600432","https://openalex.org/W2936774411","https://openalex.org/W3008039831","https://openalex.org/W3015995734","https://openalex.org/W3159481202","https://openalex.org/W3196782138","https://openalex.org/W3206996142","https://openalex.org/W4375869071","https://openalex.org/W4386066407"],"related_works":["https://openalex.org/W4390306690","https://openalex.org/W1969209172","https://openalex.org/W4385572141","https://openalex.org/W4281997472","https://openalex.org/W2961085424","https://openalex.org/W3046366884","https://openalex.org/W4224009465","https://openalex.org/W1729894570","https://openalex.org/W4221149036","https://openalex.org/W4306674287"],"abstract_inverted_index":{"Spectrogram":[0],"augmentation":[1],"(SpecAugment),":[2],"a":[3,57,82,98],"data":[4],"processing":[5],"method":[6,197],"that":[7,47,127,186],"enlarges":[8],"datasets":[9],"without":[10],"adding":[11],"new":[12],"samples,":[13],"has":[14],"been":[15],"widely":[16],"employed":[17],"in":[18,63,102],"the":[19,23,30,33,44,48,59,64,69,74,103,107,116,122,125,133,139,151,165,171,178,195,203],"fine-tuning":[20,104],"process":[21,105],"of":[22,35,124,167,180],"masked":[24,108],"model":[25,49,70,140,152],"for":[26,106,132],"audio":[27,145,168],"classification.":[28],"In":[29],"conventional":[31,65,196],"SpecAugment,":[32],"positions":[34,137],"time":[36],"masking":[37,62,112,200],"and":[38,95,198,205],"frequency":[39],"masking,":[40],"which":[41,87,147],"directly":[42],"determine":[43],"available":[45],"information":[46],"can":[50,148,190],"learn":[51,142],"from,":[52],"are":[53,128],"selected":[54],"randomly.":[55],"As":[56],"result,":[58],"random":[60,114,199],"position":[61,100],"SpecAugment":[66,85],"may":[67],"prevent":[68,150],"from":[71,153],"fully":[72],"utilizing":[73],"input":[75],"information.":[76],"To":[77],"this":[78],"end,":[79],"we":[80,175],"propose":[81],"Prediction-error-based":[83],"Adaptive":[84],"(PEAS),":[86],"incorporates":[88],"two":[89],"auxiliary":[90],"tasks":[91],"based":[92],"on":[93,121,202],"reconstruction":[94],"then":[96],"introduces":[97],"mask":[99],"selector":[101],"model.":[109,134],"Rather":[110],"than":[111],"at":[113],"positions,":[115],"proposed":[117,188],"PEAS":[118,189],"generates":[119],"masks":[120],"parts":[123],"spectrograms":[126],"hard":[129],"to":[130,141,163],"reconstruct":[131],"Masking":[135],"these":[136],"forces":[138],"more":[143],"generalized":[144],"features,":[146],"effectively":[149],"learning":[154,166],"classification":[155],"labels":[156],"by":[157],"identifying":[158],"individual":[159],"special":[160],"features.":[161],"Besides,":[162],"accelerate":[164],"features":[169],"during":[170],"early":[172],"training":[173],"epochs,":[174],"progressively":[176],"increase":[177],"proportion":[179],"adaptive":[181],"masks.":[182],"Experimental":[183],"results":[184],"demonstrate":[185],"our":[187],"match":[191],"or":[192],"outperform":[193],"both":[194],"strategy":[201],"ESC-50":[204],"Speech":[206],"Commands":[207],"V2":[208],"datasets.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}