{"id":"https://openalex.org/W4372269849","doi":"https://doi.org/10.1109/icassp49357.2023.10095265","title":"Learning to Detect Novel and Fine-Grained Acoustic Sequences Using Pretrained Audio Representations","display_name":"Learning to Detect Novel and Fine-Grained Acoustic Sequences Using Pretrained Audio Representations","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372269849","doi":"https://doi.org/10.1109/icassp49357.2023.10095265"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095265","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5059094634","display_name":"Vasudha Kowtha","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Vasudha Kowtha","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002324466","display_name":"Miquel Espi Marques","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Miquel Espi Marques","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079026336","display_name":"Jonathan Huang","orcid":"https://orcid.org/0000-0002-3428-9952"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jonathan Huang","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100444198","display_name":"Yichi Zhang","orcid":"https://orcid.org/0000-0003-0465-6341"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yichi Zhang","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048751367","display_name":"Carlos Avendano","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Carlos Avendano","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059094634"],"corresponding_institution_ids":["https://openalex.org/I4210107260"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03874804,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9955000281333923,"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":0.9696999788284302,"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":0.813858151435852},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.7590994834899902},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7190801501274109},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5871853232383728},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5780807137489319},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5334399342536926},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.5205844044685364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4644821584224701},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05399125814437866}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.813858151435852},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7590994834899902},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7190801501274109},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5871853232383728},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5780807137489319},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5334399342536926},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.5205844044685364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4644821584224701},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05399125814437866},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095265","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":26,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1821462560","https://openalex.org/W2052666245","https://openalex.org/W2194775991","https://openalex.org/W2593116425","https://openalex.org/W2768282280","https://openalex.org/W2936774411","https://openalex.org/W2962999716","https://openalex.org/W2963163009","https://openalex.org/W3015205011","https://openalex.org/W3015371781","https://openalex.org/W3015622757","https://openalex.org/W3035884675","https://openalex.org/W3094550259","https://openalex.org/W3108975329","https://openalex.org/W4205236539","https://openalex.org/W4205689591","https://openalex.org/W4289288178","https://openalex.org/W4307823382","https://openalex.org/W4312813914","https://openalex.org/W6638523607","https://openalex.org/W6746052068","https://openalex.org/W6749464311","https://openalex.org/W6752940074","https://openalex.org/W6755726434","https://openalex.org/W6758126075"],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2773965352","https://openalex.org/W4294892107","https://openalex.org/W2357748469","https://openalex.org/W2392917037"],"abstract_inverted_index":{"This":[0],"work":[1],"investigates":[2],"pretrained":[3,66,86],"audio":[4],"representations":[5,67],"for":[6,42],"few":[7,18,53,75,100],"shot":[8,19,54,76,101],"Sound":[9],"Event":[10],"Detection.":[11],"We":[12,39],"specifically":[13],"address":[14],"the":[15,60,71,91],"task":[16],"of":[17,21,64,73,98],"detection":[20],"novel":[22],"acoustic":[23,83],"sequences,":[24],"or":[25],"sound":[26],"events":[27],"with":[28],"semantically":[29],"meaningful":[30],"temporal":[31],"structure,":[32],"without":[33],"assuming":[34],"access":[35],"to":[36,51,90],"non-target":[37],"audio.":[38],"develop":[40],"procedures":[41],"pretraining":[43],"suitable":[44,89],"representations,":[45],"and":[46,70,94],"methods":[47,77],"which":[48],"transfer":[49],"them":[50],"our":[52,65,99],"learning":[55],"scenario.":[56],"Our":[57,85],"experiments":[58],"evaluate":[59],"general":[61],"purpose":[62],"utility":[63,72],"on":[68],"AudioSet,":[69],"proposed":[74,92],"via":[78],"tasks":[79],"constructed":[80],"from":[81],"real-world":[82],"sequences.":[84],"embeddings":[87],"are":[88],"task,":[93],"enable":[95],"multiple":[96],"aspects":[97],"framework.":[102]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}
