{"id":"https://openalex.org/W4415524429","doi":"https://doi.org/10.1109/mlsp62443.2025.11204215","title":"Prototypical Contrastive Learning for Improved Few Shot Audio Classification","display_name":"Prototypical Contrastive Learning for Improved Few Shot Audio Classification","publication_year":2025,"publication_date":"2025-08-31","ids":{"openalex":"https://openalex.org/W4415524429","doi":"https://doi.org/10.1109/mlsp62443.2025.11204215"},"language":null,"primary_location":{"id":"doi:10.1109/mlsp62443.2025.11204215","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5119758498","display_name":"Christos Sgouropoulos","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Christos Sgouropoulos","raw_affiliation_strings":["Institute of Informatics and Telecommunications, NCSR “DEMOKRITOS”,Multimedia Analysis Group of the Computational Intelligence Laboratory (MagCIL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics and Telecommunications, NCSR “DEMOKRITOS”,Multimedia Analysis Group of the Computational Intelligence Laboratory (MagCIL)","institution_ids":["https://openalex.org/I4210152232"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103206076","display_name":"Christos Nikou","orcid":"https://orcid.org/0009-0002-1484-192X"},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Christos Nikou","raw_affiliation_strings":["Institute of Informatics and Telecommunications, NCSR “DEMOKRITOS”,Multimedia Analysis Group of the Computational Intelligence Laboratory (MagCIL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics and Telecommunications, NCSR “DEMOKRITOS”,Multimedia Analysis Group of the Computational Intelligence Laboratory (MagCIL)","institution_ids":["https://openalex.org/I4210152232"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Stefanos Vlachos","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Stefanos Vlachos","raw_affiliation_strings":["Institute of Informatics and Telecommunications, NCSR “DEMOKRITOS”,Multimedia Analysis Group of the Computational Intelligence Laboratory (MagCIL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics and Telecommunications, NCSR “DEMOKRITOS”,Multimedia Analysis Group of the Computational Intelligence Laboratory (MagCIL)","institution_ids":["https://openalex.org/I4210152232"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049785406","display_name":"Vasileios Theiou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Vasileios Theiou","raw_affiliation_strings":["Institute of Informatics and Telecommunications, NCSR “DEMOKRITOS”,Multimedia Analysis Group of the Computational Intelligence Laboratory (MagCIL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics and Telecommunications, NCSR “DEMOKRITOS”,Multimedia Analysis Group of the Computational Intelligence Laboratory (MagCIL)","institution_ids":["https://openalex.org/I4210152232"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119758499","display_name":"Christos Foukanelis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Christos Foukanelis","raw_affiliation_strings":["Institute of Informatics and Telecommunications, NCSR “DEMOKRITOS”,Multimedia Analysis Group of the Computational Intelligence Laboratory (MagCIL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics and Telecommunications, NCSR “DEMOKRITOS”,Multimedia Analysis Group of the Computational Intelligence Laboratory (MagCIL)","institution_ids":["https://openalex.org/I4210152232"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082928814","display_name":"Theodoros Giannakopoulos","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Theodoros Giannakopoulos","raw_affiliation_strings":["Institute of Informatics and Telecommunications, NCSR “DEMOKRITOS”,Multimedia Analysis Group of the Computational Intelligence Laboratory (MagCIL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics and Telecommunications, NCSR “DEMOKRITOS”,Multimedia Analysis Group of the Computational Intelligence Laboratory (MagCIL)","institution_ids":["https://openalex.org/I4210152232"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210152232"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37619097,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9958999752998352,"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":0.9958999752998352,"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":0.9757999777793884,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9721999764442444,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6313999891281128},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.535099983215332},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.529699981212616},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5133000016212463},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.36160001158714294},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.3499999940395355},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.34310001134872437},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.33149999380111694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7857000231742859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6535000205039978},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6313999891281128},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.529699981212616},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5133000016212463},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45249998569488525},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38929998874664307},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.36160001158714294},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33079999685287476},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3100000023841858},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2879999876022339},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp62443.2025.11204215","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","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":12,"referenced_works":["https://openalex.org/W2936774411","https://openalex.org/W2949676527","https://openalex.org/W2962845248","https://openalex.org/W2962999716","https://openalex.org/W2963386851","https://openalex.org/W2963988212","https://openalex.org/W2973006577","https://openalex.org/W3015205011","https://openalex.org/W3203918617","https://openalex.org/W4294831657","https://openalex.org/W4313034431","https://openalex.org/W4372260106"],"related_works":[],"abstract_inverted_index":{"Few-shot":[0],"learning":[1,35,122],"has":[2,27],"emerged":[3],"as":[4],"a":[5,85,106,117,133],"powerful":[6],"paradigm":[7],"for":[8,59,124],"training":[9,58],"models":[10,123],"with":[11,111],"limited":[12],"labeled":[13],"data,":[14],"addressing":[15],"challenges":[16],"in":[17,30,36,132],"scenarios":[18],"where":[19],"large-scale":[20],"annotation":[21],"is":[22],"impractical.":[23],"While":[24],"extensive":[25],"research":[26],"been":[28],"conducted":[29],"the":[31,47,71,75],"image":[32],"domain,":[33],"few-shot":[34,121],"audio":[37,60],"classification":[38],"remains":[39],"relatively":[40],"underexplored.":[41],"In":[42,62],"this":[43],"work,":[44],"we":[45,64],"investigate":[46],"effect":[48],"of":[49,92,120],"integrating":[50],"supervised":[51],"contrastive":[52,77],"loss":[53,68],"into":[54,96],"prototypical":[55],"few":[56],"shot":[57],"classification.":[61],"detail,":[63],"demonstrate":[65],"that":[66],"angular":[67],"further":[69],"improves":[70],"performance":[72,131],"compared":[73],"to":[74,88],"standard":[76],"loss.":[78],"Our":[79],"method":[80],"leverages":[81],"SpecAugment":[82],"followed":[83],"by":[84],"self-attention":[86],"mechanism":[87],"encapsulate":[89],"diverse":[90],"information":[91],"augmented":[93],"input":[94],"versions":[95],"one":[97],"unified":[98],"embedding.":[99],"We":[100],"evaluate":[101],"our":[102],"approach":[103,128],"on":[104],"MetaAudio,":[105],"benchmark":[107],"including":[108],"five":[109],"datasets":[110],"predefined":[112],"splits,":[113],"standardized":[114],"preprocessing,":[115],"and":[116],"comprehensive":[118],"set":[119],"comparison.":[125],"The":[126],"proposed":[127],"achieves":[129],"state-of-the-art":[130],"5-way,":[134],"5-shot":[135],"setting.":[136]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-24T00:00:00"}