{"id":"https://openalex.org/W4408354391","doi":"https://doi.org/10.1109/icassp49660.2025.10890012","title":"Effective Techniques for Scaling Audio Encoder Pretraining","display_name":"Effective Techniques for Scaling Audio Encoder Pretraining","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354391","doi":"https://doi.org/10.1109/icassp49660.2025.10890012"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890012","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":"https://openalex.org/A5081897616","display_name":"Byeonggeun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Byeonggeun Kim","raw_affiliation_strings":["Amazon AGI,Bellevue,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI,Bellevue,United States","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094178977","display_name":"Andrew Bydlon","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Bydlon","raw_affiliation_strings":["Amazon AGI,Boston,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI,Boston,United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101986528","display_name":"Qingming Tang","orcid":"https://orcid.org/0000-0002-2670-4917"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qingming Tang","raw_affiliation_strings":["Amazon AGI,Boston,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI,Boston,United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058452657","display_name":"Huy Phan","orcid":"https://orcid.org/0000-0003-4096-785X"},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Huy Phan","raw_affiliation_strings":["Amazon AGI,Cambridge,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI,Cambridge,United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020775828","display_name":"Chieh-Chi Kao","orcid":"https://orcid.org/0000-0002-1161-3959"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chieh-Chi Kao","raw_affiliation_strings":["Amazon AGI,Bellevue,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI,Bellevue,United States","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375792","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0002-2980-6281"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["Amazon AGI,Boston,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI,Boston,United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100407094","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0003-0906-445X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["Amazon AGI,Boston,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI,Boston,United States","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4985,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61120637,"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/T12759","display_name":"Vehicle Noise and Vibration Control","score":0.8960000276565552,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12759","display_name":"Vehicle Noise and Vibration Control","score":0.8960000276565552,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.8474000096321106,"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"}},{"id":"https://openalex.org/T10534","display_name":"Structural Health Monitoring Techniques","score":0.7657999992370605,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural 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/computer-science","display_name":"Computer science","score":0.7691408395767212},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6651920080184937},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5595758557319641},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5238785147666931},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07511621713638306},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.06221535801887512}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7691408395767212},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6651920080184937},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5595758557319641},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5238785147666931},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07511621713638306},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.06221535801887512},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890012","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2936774411","https://openalex.org/W2963686995","https://openalex.org/W3015371781","https://openalex.org/W3020336359","https://openalex.org/W3035524453","https://openalex.org/W3175898847","https://openalex.org/W3197580070","https://openalex.org/W4225299287","https://openalex.org/W4312097006","https://openalex.org/W4313156423","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4381786045","https://openalex.org/W4404740148","https://openalex.org/W6755207826","https://openalex.org/W6755977528","https://openalex.org/W6757817989","https://openalex.org/W6784333009","https://openalex.org/W6785932716","https://openalex.org/W6840200333","https://openalex.org/W6847363464","https://openalex.org/W6847495150","https://openalex.org/W6848208918","https://openalex.org/W6853393314","https://openalex.org/W6856659047","https://openalex.org/W6857944214","https://openalex.org/W6859084170","https://openalex.org/W6859099255","https://openalex.org/W6870122244"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"advancements":[3],"in":[4,26,35,61],"audio":[5,46,54,162],"pretraining":[6],"objectives":[7],"designed":[8],"to":[9,145],"generate":[10],"semantically":[11],"rich":[12],"embeddings,":[13],"capable":[14],"of":[15,20,44,72,116,158,172],"addressing":[16],"a":[17,68,87,102],"wide":[18],"range":[19],"audio-related":[21],"tasks.":[22,152],"Despite":[23],"significant":[24],"progress":[25],"the":[27,41,92,109,114,119,131,156,160,173],"field,":[28],"current":[29],"methods":[30,148],"often":[31],"emphasize":[32],"full":[33,137],"fine-tuning":[34,63],"downstream":[36,151],"applications,":[37],"which":[38,95],"can":[39],"obscure":[40],"true":[42],"potential":[43,157],"pretrained":[45],"encoders.":[47],"In":[48],"this":[49],"study,":[50],"we":[51,79,112,154],"present":[52],"an":[53],"encoder":[55,132],"that":[56],"achieves":[57],"stateof-the-art":[58],"(SOTA)":[59],"performances":[60],"both":[62,118],"and":[64,83,122],"linear":[65,126],"probing,":[66],"utilizing":[67],"carefully":[69],"curated":[70],"set":[71],"pragmatic":[73],"techniques.":[74],"Building":[75],"on":[76],"previous":[77],"research,":[78],"incorporate":[80],"masked":[81],"prediction":[82],"introduce":[84],"SpecAug":[85],"within":[86],"curriculum":[88],"masking":[89],"strategy":[90],"at":[91],"patch":[93],"level,":[94],"progressively":[96],"increases":[97],"training":[98],"difficulty,":[99],"along":[100],"with":[101],"mask-aware":[103],"position":[104],"bias.":[105],"To":[106],"comprehensively":[107],"assess":[108],"encoder\u2019s":[110],"capabilities,":[111],"examine":[113],"impact":[115],"scaling":[117],"dataset":[120],"size":[121],"model":[123,140],"capacity,":[124],"conducting":[125],"probing":[127],"evaluations":[128],"while":[129],"keeping":[130],"frozen":[133],"as":[134,136,166],"well":[135],"fine-tuning.":[138],"Our":[139],"demonstrates":[141],"superior":[142],"performance":[143],"compared":[144],"recent":[146],"SOTA":[147],"across":[149],"various":[150],"Additionally,":[153],"explore":[155],"tokenizing":[159],"resulting":[161],"embeddings":[163],"for":[164],"use":[165],"discrete":[167],"inputs,":[168],"enhancing":[169],"our":[170],"understanding":[171],"model\u2019s":[174],"capabilities.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}