{"id":"https://openalex.org/W4416798782","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249268","title":"Meta-Learning with Pretrained Audio Representations Enables One-Shot Acoustic Signal Classification","display_name":"Meta-Learning with Pretrained Audio Representations Enables One-Shot Acoustic Signal Classification","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798782","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249268"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5103659787","display_name":"Haoxiang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoxiang Wu","raw_affiliation_strings":["Center of Intelligent Acoustics and Immersive Communications, Northwestern Polytechnical University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Intelligent Acoustics and Immersive Communications, Northwestern Polytechnical University,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021677656","display_name":"Zhengqiao Zhao","orcid":"https://orcid.org/0000-0001-6873-6098"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqiao Zhao","raw_affiliation_strings":["Center of Intelligent Acoustics and Immersive Communications, Northwestern Polytechnical University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Intelligent Acoustics and Immersive Communications, Northwestern Polytechnical University,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056129529","display_name":"Jingdong Chen","orcid":"https://orcid.org/0000-0003-0083-9247"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingdong Chen","raw_affiliation_strings":["Center of Intelligent Acoustics and Immersive Communications, Northwestern Polytechnical University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Intelligent Acoustics and Immersive Communications, Northwestern Polytechnical University,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109041104","display_name":"Jacob Benesty","orcid":null},"institutions":[{"id":"https://openalex.org/I49663120","display_name":"Universit\u00e9 du Qu\u00e9bec","ror":"https://ror.org/010gxg263","country_code":"CA","type":"education","lineage":["https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jacob Benesty","raw_affiliation_strings":["University of Quebec,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Quebec,Canada","institution_ids":["https://openalex.org/I49663120"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39321983,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"172","last_page":"176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.7623999714851379,"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":0.7623999714851379,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.039400000125169754,"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/T12419","display_name":"Phonocardiography and Auscultation Techniques","score":0.01360000018030405,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8021000027656555},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6455000042915344},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5285999774932861},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4975000023841858},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4489000141620636},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3752000033855438},{"id":"https://openalex.org/keywords/bioacoustics","display_name":"Bioacoustics","score":0.3732999861240387},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3646000027656555}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8021000027656555},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7311999797821045},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6455000042915344},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6151000261306763},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5285999774932861},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4975000023841858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48910000920295715},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4489000141620636},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3646000027656555},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.34529998898506165},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.32679998874664307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29840001463890076},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.27000001072883606},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2689000070095062},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2658376355","display_name":null,"funder_award_id":"2024YFF0505502","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2327501763","https://openalex.org/W2466903746","https://openalex.org/W2593116425","https://openalex.org/W2917792613","https://openalex.org/W2963022469","https://openalex.org/W2963070905","https://openalex.org/W2973049979","https://openalex.org/W2986739609","https://openalex.org/W3169708801","https://openalex.org/W3196974791","https://openalex.org/W3209059054","https://openalex.org/W4205236539","https://openalex.org/W4294831657","https://openalex.org/W4372266552","https://openalex.org/W4375869388","https://openalex.org/W4388428078","https://openalex.org/W4406858736"],"related_works":[],"abstract_inverted_index":{"Few-shot":[0],"acoustic":[1,16,34,118,123,169],"signal":[2,35,119],"classification":[3,27,36,67,120,155,182],"remains":[4],"a":[5,64,72,87,100],"challenging":[6],"problem":[7],"due":[8],"to":[9,43,78,107],"the":[10,60,83,113,143,176],"high":[11],"diversity":[12],"and":[13,18,129],"variability":[14],"of":[15,21,63,86,153,179],"data":[17,167],"limited":[19],"availability":[20],"labeled":[22],"samples.":[23],"While":[24],"pretrained":[25,65],"audio":[26,66,181],"models":[28,183],"have":[29],"proven":[30],"effective":[31,105],"for":[32,165,189],"various":[33],"tasks,":[37,121],"fine-tuning":[38],"them":[39],"can":[40],"still":[41],"lead":[42],"overfitting":[44],"in":[45,151],"low-resource":[46],"settings.":[47],"In":[48],"this":[49],"work,":[50],"we":[51,70],"proposes":[52],"an":[53,162],"attention-based":[54],"meta-learning":[55,102],"framework":[56,140,188],"that":[57,137],"operates":[58],"on":[59,116],"hidden":[61,84],"states":[62,85],"model.":[68],"Specifically,":[69],"introduce":[71],"trainable":[73],"hierarchical":[74],"additive":[75],"attention":[76,95],"module":[77],"extract":[79],"meaningful":[80],"features":[81],"from":[82],"large-scale":[88],"pre-trained":[89,180],"Audio":[90],"Spectrogram":[91],"Transformer":[92],"(AST).":[93],"The":[94],"mechanism":[96],"is":[97],"trained":[98],"with":[99,186],"simple":[101],"paradigm,":[103],"enabling":[104],"adaptation":[106],"one-shot":[108,154],"learning":[109],"tasks.":[110],"We":[111],"evaluates":[112],"proposed":[114,139],"model":[115],"multiple":[117],"including":[122],"scene":[124],"classification,":[125],"sound":[126],"event":[127],"recognition":[128,171],"underwater":[130],"vessel":[131],"noise":[132],"classification.":[133],"Experimental":[134],"results":[135],"demonstrate":[136,175],"our":[138],"substantially":[141],"outperforms":[142],"existing":[144],"methods":[145],"such":[146],"as":[147],"CNN-based":[148],"prototypical":[149],"networks":[150],"terms":[152],"accuracy.":[156],"This":[157],"research":[158],"not":[159],"only":[160],"provides":[161],"efficient":[163],"solution":[164],"low":[166],"resource":[168],"pattern":[170],"tasks":[172],"but":[173],"also":[174],"strong":[177],"potential":[178],"when":[184],"combined":[185],"metalearning":[187],"few-shot":[190],"learning.":[191]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}