{"id":"https://openalex.org/W4408355740","doi":"https://doi.org/10.1109/icassp49660.2025.10890881","title":"Pre-training with Synthetic Patterns for Audio","display_name":"Pre-training with Synthetic Patterns for Audio","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355740","doi":"https://doi.org/10.1109/icassp49660.2025.10890881"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890881","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890881","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":null,"display_name":"Yuchi Ishikawa","orcid":null},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuchi Ishikawa","raw_affiliation_strings":["Keio University,LY Corporation,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keio University,LY Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113730169","display_name":"Tatsuya Komatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Komatsu","raw_affiliation_strings":["LY Corporation,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LY Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070908826","display_name":"Yoshimitsu Aoki","orcid":"https://orcid.org/0000-0001-7361-0027"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshimitsu Aoki","raw_affiliation_strings":["Keio University,Kanagawa,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keio University,Kanagawa,Japan","institution_ids":["https://openalex.org/I203951103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0421,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72215768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"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":0.7578999996185303,"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":0.7578999996185303,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.7028999924659729,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.700158953666687},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.610957682132721},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.447870135307312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3270125389099121}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.700158953666687},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.610957682132721},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.447870135307312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3270125389099121},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890881","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890881","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":41,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2030931454","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2103559027","https://openalex.org/W2108598243","https://openalex.org/W2145023731","https://openalex.org/W2593116425","https://openalex.org/W2982346427","https://openalex.org/W3008480565","https://openalex.org/W3015371781","https://openalex.org/W3094550259","https://openalex.org/W3162244132","https://openalex.org/W3196974791","https://openalex.org/W3205475937","https://openalex.org/W3205743929","https://openalex.org/W3206996142","https://openalex.org/W3210163254","https://openalex.org/W4205689591","https://openalex.org/W4210836801","https://openalex.org/W4213414377","https://openalex.org/W4313013151","https://openalex.org/W4313156423","https://openalex.org/W4372266552","https://openalex.org/W4375869340","https://openalex.org/W4385572536","https://openalex.org/W4386075504","https://openalex.org/W4390874283","https://openalex.org/W4401597538","https://openalex.org/W4403947211","https://openalex.org/W6736723571","https://openalex.org/W6739901393","https://openalex.org/W6750665317","https://openalex.org/W6756597712","https://openalex.org/W6784333009","https://openalex.org/W6787972765","https://openalex.org/W6809947431","https://openalex.org/W6810265253","https://openalex.org/W6840200333","https://openalex.org/W6847435242","https://openalex.org/W6869681038"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,138],"propose":[4],"to":[5,47,82,115,128,176],"pre-train":[6],"audio":[7,15,74,147],"encoders":[8],"using":[9],"synthetic":[10,78,89,108,151,161],"patterns":[11,55,162],"instead":[12],"of":[13,21,135,145,160],"real":[14,94,121,129],"data.":[16,59,90],"Our":[17,167],"proposed":[18],"framework":[19,35,111,172],"consists":[20],"two":[22],"key":[23,85],"elements.":[24],"The":[25,153],"first":[26],"one":[27],"is":[28,62,65,88,96],"Masked":[29],"Autoencoder":[30],"(MAE),":[31],"a":[32,143],"self-supervised":[33],"learning":[34],"that":[36,170],"learns":[37],"from":[38,41,98],"reconstructing":[39],"data":[40],"randomly":[42],"masked":[43],"counterparts.":[44],"MAEs":[45,106],"tend":[46],"focus":[48],"on":[49,179],"low-level":[50],"information":[51],"such":[52],"as":[53],"visual":[54],"and":[56,100,107,149,181],"regularities":[57],"within":[58],"Therefore,":[60],"it":[61,71],"unimportant":[63],"what":[64],"portrayed":[66],"in":[67],"the":[68,83,113,125,133],"input,":[69],"whether":[70],"be":[72],"images,":[73],"mel-spectrograms,":[75],"or":[76],"even":[77],"patterns.":[79],"This":[80],"leads":[81],"second":[84],"element,":[86],"which":[87,158],"Synthetic":[91],"data,":[92,122],"unlike":[93],"audio,":[95],"free":[97],"privacy":[99],"licensing":[101],"infringement":[102],"issues.":[103],"By":[104],"combining":[105],"patterns,":[109],"our":[110,136,171],"enables":[112],"model":[114],"learn":[116],"generalized":[117],"feature":[118],"representations":[119],"without":[120],"while":[123],"addressing":[124],"issues":[126],"related":[127],"audio.":[130,166],"To":[131],"evaluate":[132],"efficacy":[134],"framework,":[137],"conduct":[139],"extensive":[140],"experiments":[141,154],"across":[142],"total":[144],"13":[146],"tasks":[148],"17":[150],"datasets.":[152],"provide":[155],"insights":[156],"into":[157],"types":[159],"are":[163],"effective":[164],"for":[165],"results":[168],"demonstrate":[169],"achieves":[173],"performance":[174],"comparable":[175],"models":[177],"pre-trained":[178],"AudioSet-2M":[180],"partially":[182],"outperforms":[183],"image-based":[184],"pre-training":[185],"methods.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2025-10-10T00:00:00"}