{"id":"https://openalex.org/W3162549784","doi":"https://doi.org/10.1109/icassp39728.2021.9414916","title":"Learning Separable Time-Frequency Filterbanks for Audio Classification","display_name":"Learning Separable Time-Frequency Filterbanks for Audio Classification","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162549784","doi":"https://doi.org/10.1109/icassp39728.2021.9414916","mag":"3162549784"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414916","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/A5102721941","display_name":"Jie Pu","orcid":"https://orcid.org/0000-0002-5813-1201"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jie Pu","raw_affiliation_strings":["Imperial College,Department of Computing,London,UK"],"affiliations":[{"raw_affiliation_string":"Imperial College,Department of Computing,London,UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050734738","display_name":"Yannis Panagakis","orcid":"https://orcid.org/0000-0003-0153-5210"},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Yannis Panagakis","raw_affiliation_strings":["University of Athens,Department of Informatics and Telecommunications,Greece"],"affiliations":[{"raw_affiliation_string":"University of Athens,Department of Informatics and Telecommunications,Greece","institution_ids":["https://openalex.org/I200777214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016033078","display_name":"Maja Panti\u0107","orcid":"https://orcid.org/0000-0002-3620-5986"},"institutions":[{"id":"https://openalex.org/I4210111288","display_name":"Meta (United Kingdom)","ror":"https://ror.org/020ye1821","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210111288","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maja Pantic","raw_affiliation_strings":["Imperial College,Department of Computing,London,UK","Facebook AI Research, London, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College,Department of Computing,London,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Facebook AI Research, London, UK","institution_ids":["https://openalex.org/I4210111288"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102721941"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.6094,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65584855,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"23","issue":null,"first_page":"3000","last_page":"3004"},"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":0.9995999932289124,"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":0.9948999881744385,"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/spectrogram","display_name":"Spectrogram","score":0.8225137591362},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7735501527786255},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.6709172129631042},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5880126357078552},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5099555253982544},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4953214228153229},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.47451847791671753},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4644807279109955},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4638630747795105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4593326151371002},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4557575285434723},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.449733167886734},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.41825181245803833},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39396414160728455},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.20589697360992432},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08319902420043945}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8225137591362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7735501527786255},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6709172129631042},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5880126357078552},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5099555253982544},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4953214228153229},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.47451847791671753},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4644807279109955},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4638630747795105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4593326151371002},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4557575285434723},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.449733167886734},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.41825181245803833},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39396414160728455},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.20589697360992432},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08319902420043945},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414916","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1524333225","https://openalex.org/W1533861849","https://openalex.org/W1635512741","https://openalex.org/W1995562189","https://openalex.org/W2038484192","https://openalex.org/W2086384421","https://openalex.org/W2095147901","https://openalex.org/W2097117768","https://openalex.org/W2128681980","https://openalex.org/W2157498370","https://openalex.org/W2163605009","https://openalex.org/W2183341477","https://openalex.org/W2612445135","https://openalex.org/W2613718673","https://openalex.org/W2619697695","https://openalex.org/W2804619531","https://openalex.org/W2805281238","https://openalex.org/W2810934215","https://openalex.org/W2888992773","https://openalex.org/W2945837706","https://openalex.org/W2962756039","https://openalex.org/W2964052309","https://openalex.org/W2995233853","https://openalex.org/W3000389243","https://openalex.org/W4293665662","https://openalex.org/W4297775537","https://openalex.org/W6620707391","https://openalex.org/W6631362777","https://openalex.org/W6631943919","https://openalex.org/W6684191040","https://openalex.org/W6729831399","https://openalex.org/W6737664043","https://openalex.org/W6752030128","https://openalex.org/W6771763809"],"related_works":["https://openalex.org/W3006943036","https://openalex.org/W3191046242","https://openalex.org/W4205364923","https://openalex.org/W4299487748","https://openalex.org/W4206493799","https://openalex.org/W4213225422","https://openalex.org/W4294031299","https://openalex.org/W2605281151","https://openalex.org/W4310989423","https://openalex.org/W3162549784"],"abstract_inverted_index":{"State-of-the-art":[0],"audio":[1,25,54],"classification":[2],"systems":[3],"often":[4],"apply":[5],"deep":[6],"neural":[7],"networks":[8,26],"on":[9,129],"hand-crafted":[10],"features":[11,18],"(e.g.,":[12],"spectrogram-based":[13],"representations),":[14],"instead":[15],"of":[16,29,98,103,136],"learning":[17],"directly":[19,56],"from":[20,57],"raw":[21,58],"audio.":[22],"Moreover,":[23],"these":[24,130],"have":[27],"millions":[28],"unknown":[30],"parameters":[31],"need":[32],"to":[33,52,78],"be":[34],"learned,":[35],"which":[36],"causes":[37],"a":[38,71,85],"great":[39],"demand":[40],"for":[41],"computational":[42],"resources":[43],"and":[44,60,91,95,119],"training":[45,67,94,137],"data.":[46],"In":[47,74],"this":[48],"paper,":[49],"we":[50,76],"aim":[51],"learn":[53,79],"representations":[55],"audio,":[59],"at":[61],"the":[62,104],"same":[63],"time":[64],"mitigate":[65],"its":[66,127],"burden":[68],"by":[69,109],"employing":[70],"light-weight":[72],"architecture.":[73],"particular,":[75],"propose":[77],"separable":[80],"filters,":[81],"parametrized":[82],"with":[83],"only":[84],"few":[86],"variables,":[87],"namely":[88,115],"center":[89],"frequency":[90],"bandwidth,":[92],"facilitating":[93],"offering":[96],"interpretability":[97],"learned":[99],"representations.":[100],"The":[101],"generality":[102],"proposed":[105],"method":[106],"is":[107,139],"demonstrated":[108],"applying":[110],"it":[111],"onto":[112],"two":[113],"applications,":[114,131],"1)":[116],"speaker":[117],"identification":[118],"2)":[120],"acoustic":[121],"event":[122],"recognition.":[123],"Experimental":[124],"results":[125],"indicate":[126],"effectiveness":[128],"especially":[132],"when":[133],"small":[134],"amount":[135],"data":[138],"available.":[140]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}