{"id":"https://openalex.org/W4408353596","doi":"https://doi.org/10.1109/icassp49660.2025.10888942","title":"Effective Pre-Training of Audio Transformers for Sound Event Detection","display_name":"Effective Pre-Training of Audio Transformers for Sound Event Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353596","doi":"https://doi.org/10.1109/icassp49660.2025.10888942"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888942","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/A5103009549","display_name":"Florian Schmid","orcid":"https://orcid.org/0009-0007-4988-6067"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Florian Schmid","raw_affiliation_strings":["Johannes Kepler University,Institute of Computational Perception,Linz,Austria"],"affiliations":[{"raw_affiliation_string":"Johannes Kepler University,Institute of Computational Perception,Linz,Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091952748","display_name":"Tobias Morocutti","orcid":null},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Tobias Morocutti","raw_affiliation_strings":["Johannes Kepler University,Institute of Computational Perception,Linz,Austria"],"affiliations":[{"raw_affiliation_string":"Johannes Kepler University,Institute of Computational Perception,Linz,Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064606318","display_name":"Francesco Foscarin","orcid":"https://orcid.org/0000-0003-4634-7475"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Francesco Foscarin","raw_affiliation_strings":["Johannes Kepler University,Institute of Computational Perception,Linz,Austria"],"affiliations":[{"raw_affiliation_string":"Johannes Kepler University,Institute of Computational Perception,Linz,Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101525853","display_name":"Jan Schl\u00fcter","orcid":"https://orcid.org/0000-0003-3862-6888"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Jan Schl\u00fcter","raw_affiliation_strings":["Johannes Kepler University,Institute of Computational Perception,Linz,Austria"],"affiliations":[{"raw_affiliation_string":"Johannes Kepler University,Institute of Computational Perception,Linz,Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084326954","display_name":"Paul Primus","orcid":null},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Paul Primus","raw_affiliation_strings":["Johannes Kepler University,Institute of Computational Perception,Linz,Austria"],"affiliations":[{"raw_affiliation_string":"Johannes Kepler University,Institute of Computational Perception,Linz,Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003768123","display_name":"Gerhard Widmer","orcid":"https://orcid.org/0000-0003-3531-1282"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Gerhard Widmer","raw_affiliation_strings":["Johannes Kepler University,Institute of Computational Perception,Linz,Austria"],"affiliations":[{"raw_affiliation_string":"Johannes Kepler University,Institute of Computational Perception,Linz,Austria","institution_ids":["https://openalex.org/I121883995"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103009549"],"corresponding_institution_ids":["https://openalex.org/I121883995"],"apc_list":null,"apc_paid":null,"fwci":14.1673,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.991469,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"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":0.9969000220298767,"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":0.9969000220298767,"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":0.9843999743461609,"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":0.9661999940872192,"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/computer-science","display_name":"Computer science","score":0.6379846334457397},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5651393532752991},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5005826950073242},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4684073328971863},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4412384629249573},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.42138347029685974},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2816980481147766},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2765886187553406},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20387405157089233},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.18693560361862183},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.16872954368591309},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07052150368690491}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6379846334457397},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5651393532752991},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5005826950073242},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4684073328971863},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4412384629249573},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.42138347029685974},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2816980481147766},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2765886187553406},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20387405157089233},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.18693560361862183},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.16872954368591309},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07052150368690491},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/icassp49660.2025.10888942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888942","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":[{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W153185079","https://openalex.org/W2593116425","https://openalex.org/W2953183526","https://openalex.org/W2959539607","https://openalex.org/W3015190346","https://openalex.org/W3094550259","https://openalex.org/W3162999565","https://openalex.org/W3196974791","https://openalex.org/W3203468141","https://openalex.org/W3205475937","https://openalex.org/W3206996142","https://openalex.org/W4224920041","https://openalex.org/W4226442948","https://openalex.org/W4283693214","https://openalex.org/W4293363567","https://openalex.org/W4372260403","https://openalex.org/W4372267124","https://openalex.org/W4375869340","https://openalex.org/W4385488967","https://openalex.org/W4385822843","https://openalex.org/W4390738640","https://openalex.org/W4392904001","https://openalex.org/W4392904244","https://openalex.org/W4394862844","https://openalex.org/W4400679783","https://openalex.org/W4402112408","https://openalex.org/W4402115919","https://openalex.org/W4402576566","https://openalex.org/W6784333009","https://openalex.org/W6787473312","https://openalex.org/W6788135285","https://openalex.org/W6809596386","https://openalex.org/W6809947431","https://openalex.org/W6840200333","https://openalex.org/W6848208918","https://openalex.org/W6869582388","https://openalex.org/W6870090694","https://openalex.org/W6875730839"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W611303608","https://openalex.org/W4313595395","https://openalex.org/W2312783472","https://openalex.org/W2909748163"],"abstract_inverted_index":{"We":[0,74],"propose":[1],"a":[2,23,34,49],"pre-training":[3,19],"pipeline":[4],"for":[5,9,88],"audio":[6],"spectrogram":[7],"transformers":[8],"frame-level":[10,30,60,64],"sound":[11,65,89],"event":[12,66,90],"detection":[13,67,91],"tasks.":[14,92],"On":[15],"top":[16],"of":[17],"common":[18],"steps,":[20],"we":[21,47],"add":[22],"meticulously":[24],"designed":[25],"training":[26],"routine":[27],"on":[28,58,63],"AudioSet":[29,59],"annotations.":[31],"This":[32],"includes":[33],"balanced":[35],"sampler,":[36],"aggressive":[37],"data":[38],"augmentation,":[39],"and":[40,62],"ensemble":[41],"knowledge":[42],"distillation.":[43],"For":[44],"five":[45],"transformers,":[46],"obtain":[48],"substantial":[50],"performance":[51],"improvement":[52],"over":[53],"previously":[54],"available":[55],"checkpoints":[56,78],"both":[57],"predictions":[61],"downstream":[68],"tasks,":[69],"confirming":[70],"our":[71],"pipeline\u2019s":[72],"effectiveness.":[73],"publish":[75],"the":[76],"resulting":[77],"that":[79],"researchers":[80],"can":[81],"directly":[82],"fine-tune":[83],"to":[84],"build":[85],"high-performance":[86],"models":[87]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}
