{"id":"https://openalex.org/W3161026535","doi":"https://doi.org/10.1109/icassp39728.2021.9414229","title":"Efficient End-to-End Audio Embeddings Generation for Audio Classification on Target Applications","display_name":"Efficient End-to-End Audio Embeddings Generation for Audio Classification on Target Applications","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161026535","doi":"https://doi.org/10.1109/icassp39728.2021.9414229","mag":"3161026535"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5077970102","display_name":"Paulo Lopez\u2010Meyer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133208","display_name":"Centro de Investigaci\u00f3n y Proyectos en Ambiente y Desarrollo","ror":"https://ror.org/03dgk3y06","country_code":"MX","type":"other","lineage":["https://openalex.org/I4210133208"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Paulo Lopez-Meyer","raw_affiliation_strings":["Intel Labs, Intel Corp, Zapopan, JAL, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs, Intel Corp, Zapopan, JAL, Mexico","institution_ids":["https://openalex.org/I4210133208"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001904268","display_name":"Juan A. del Hoyo Ontiveros","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133208","display_name":"Centro de Investigaci\u00f3n y Proyectos en Ambiente y Desarrollo","ror":"https://ror.org/03dgk3y06","country_code":"MX","type":"other","lineage":["https://openalex.org/I4210133208"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Juan A. del Hoyo Ontiveros","raw_affiliation_strings":["Intel Labs, Intel Corp, Zapopan, JAL, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs, Intel Corp, Zapopan, JAL, Mexico","institution_ids":["https://openalex.org/I4210133208"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014469274","display_name":"Hong Lu","orcid":"https://orcid.org/0000-0003-3062-7763"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Lu","raw_affiliation_strings":["Intel Labs, Intel Corp, Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs, Intel Corp, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088131608","display_name":"Georg Stemmer","orcid":"https://orcid.org/0009-0008-9871-2423"},"institutions":[{"id":"https://openalex.org/I4210094487","display_name":"Intel (Germany)","ror":"https://ror.org/00m2x0g47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210094487"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georg Stemmer","raw_affiliation_strings":["Intel Labs, Intel Corp, Neubiberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs, Intel Corp, Neubiberg, Germany","institution_ids":["https://openalex.org/I4210094487"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3972,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.93204793,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"601","last_page":"605"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9993000030517578,"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":0.9937999844551086,"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":0.8554098606109619},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6131643652915955},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.612583339214325},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6099827885627747},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.5657917261123657},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5178673267364502},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.501793384552002},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4911322295665741},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44727379083633423},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35732877254486084},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09395715594291687},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.09236663579940796},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.07240498065948486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8554098606109619},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6131643652915955},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.612583339214325},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6099827885627747},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.5657917261123657},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5178673267364502},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.501793384552002},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4911322295665741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44727379083633423},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35732877254486084},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09395715594291687},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.09236663579940796},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.07240498065948486},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/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/icassp39728.2021.9414229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":36,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1989831790","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2086384421","https://openalex.org/W2149933564","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2593451766","https://openalex.org/W2603326847","https://openalex.org/W2612445135","https://openalex.org/W2765407302","https://openalex.org/W2901459357","https://openalex.org/W2939574508","https://openalex.org/W2962756039","https://openalex.org/W2962835968","https://openalex.org/W2963399829","https://openalex.org/W2963838685","https://openalex.org/W2982346427","https://openalex.org/W2982683041","https://openalex.org/W3032502780","https://openalex.org/W3094550259","https://openalex.org/W4289288178","https://openalex.org/W4293665662","https://openalex.org/W4297775537","https://openalex.org/W4298091485","https://openalex.org/W4299518610","https://openalex.org/W6637373629","https://openalex.org/W6682132143","https://openalex.org/W6727253422","https://openalex.org/W6729831399","https://openalex.org/W6735819631","https://openalex.org/W6737664043","https://openalex.org/W6745136726","https://openalex.org/W6755726434","https://openalex.org/W6779341498"],"related_works":["https://openalex.org/W2356602486","https://openalex.org/W2351992668","https://openalex.org/W2324828474","https://openalex.org/W2374315191","https://openalex.org/W2391207559","https://openalex.org/W2384715785","https://openalex.org/W2349624418","https://openalex.org/W2064459023","https://openalex.org/W2384611437","https://openalex.org/W2347873412"],"abstract_inverted_index":{"We":[0,88],"describe":[1],"a":[2,37,57,66,122],"general-purpose":[3],"end-to-end":[4,31,119],"audio":[5,28,44,59,68,84,132],"embeddings":[6,32,98],"generator":[7,33,99],"that":[8,62,117],"can":[9,71],"be":[10,73],"easily":[11],"adapted":[12],"to":[13,23,128],"various":[14],"acoustic":[15],"scene":[16],"and":[17,94,106,125],"event":[18],"classification":[19,85],"applications.":[20],"In":[21],"contrast":[22],"many":[24],"other":[25],"models":[26],"for":[27,82,109],"classification,":[29],"this":[30,118],"does":[34],"not":[35],"require":[36],"separate":[38],"feature":[39],"extraction":[40],"step,":[41],"but":[42],"processes":[43],"samples":[45],"directly":[46],"which":[47],"simplifies":[48],"its":[49],"porting":[50],"into":[51],"hardware":[52],"platforms.":[53],"Our":[54],"approach":[55,120],"learns":[56],"generic":[58],"embedding":[60],"representation":[61],"is":[63],"pre-trained":[64],"on":[65,100],"large":[67],"dataset.":[69],"It":[70],"then":[72],"fine-tuned":[74],"via":[75],"transfer":[76,91],"learning":[77,92],"with":[78],"limited":[79],"data":[80],"requirements":[81],"an":[83],"target":[86],"application.":[87],"compare":[89],"different":[90,110],"strategies":[93],"evaluate":[95],"the":[96],"proposed":[97],"three":[101],"popular":[102],"publicly":[103],"available":[104],"datasets,":[105],"report":[107],"results":[108,115],"model":[111],"sizes.":[112],"The":[113],"experimental":[114],"show":[116],"presents":[121],"scalable,":[123],"efficient,":[124],"competitive":[126],"alternative":[127],"more":[129],"common":[130],"spectral-based":[131],"classifiers.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}