{"id":"https://openalex.org/W4372348057","doi":"https://doi.org/10.1109/icassp49357.2023.10095474","title":"Learnable Frontends That Do Not Learn: Quantifying Sensitivity To Filterbank Initialisation","display_name":"Learnable Frontends That Do Not Learn: Quantifying Sensitivity To Filterbank Initialisation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372348057","doi":"https://doi.org/10.1109/icassp49357.2023.10095474"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095474","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":"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/A5053519224","display_name":"Mark Anderson","orcid":"https://orcid.org/0000-0002-6598-6806"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Mark Anderson","raw_affiliation_strings":["Trinity College Dublin,SIGMEDIA Lab, School of Engineering,Ireland","SIGMEDIA Lab, School of Engineering, Trinity College Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Trinity College Dublin,SIGMEDIA Lab, School of Engineering,Ireland","institution_ids":["https://openalex.org/I205274468"]},{"raw_affiliation_string":"SIGMEDIA Lab, School of Engineering, Trinity College Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":["University of Eastern Finland,School of Computing,Joensuu,Finland","School of Computing, University of Eastern Finland, Joensuu, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Eastern Finland,School of Computing,Joensuu,Finland","institution_ids":["https://openalex.org/I175532246"]},{"raw_affiliation_string":"School of Computing, University of Eastern Finland, Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042231269","display_name":"Naomi Harte","orcid":"https://orcid.org/0000-0002-9274-209X"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Naomi Harte","raw_affiliation_strings":["Trinity College Dublin,SIGMEDIA Lab, School of Engineering,Ireland","SIGMEDIA Lab, School of Engineering, Trinity College Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Trinity College Dublin,SIGMEDIA Lab, School of Engineering,Ireland","institution_ids":["https://openalex.org/I205274468"]},{"raw_affiliation_string":"SIGMEDIA Lab, School of Engineering, Trinity College Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2083,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80365511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"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/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"}},"topics":[{"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/T11309","display_name":"Music 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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.8963227272033691},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6983577609062195},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.5962072610855103},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5443200469017029},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5014376640319824},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46692463755607605},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.42001938819885254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3568241596221924},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.19339317083358765},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.17349091172218323},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1426505446434021}],"concepts":[{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.8963227272033691},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6983577609062195},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.5962072610855103},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5443200469017029},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5014376640319824},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46692463755607605},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.42001938819885254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3568241596221924},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.19339317083358765},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.17349091172218323},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1426505446434021},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095474","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1966129222","https://openalex.org/W2003212690","https://openalex.org/W2078124810","https://openalex.org/W2111460811","https://openalex.org/W2132481658","https://openalex.org/W2148154194","https://openalex.org/W2168198747","https://openalex.org/W2172213580","https://openalex.org/W2312381234","https://openalex.org/W2553581788","https://openalex.org/W2899201823","https://openalex.org/W2955425717","https://openalex.org/W2962901777","https://openalex.org/W2963071736","https://openalex.org/W2963175699","https://openalex.org/W2963263347","https://openalex.org/W2963881567","https://openalex.org/W2964052309","https://openalex.org/W2973133192","https://openalex.org/W2995588677","https://openalex.org/W3034535039","https://openalex.org/W3196368020","https://openalex.org/W3198408613","https://openalex.org/W3201535109","https://openalex.org/W4226051760","https://openalex.org/W4287372095","https://openalex.org/W4312470705","https://openalex.org/W4312856903","https://openalex.org/W6726497184","https://openalex.org/W6762718338","https://openalex.org/W6789403026","https://openalex.org/W6800400543","https://openalex.org/W7005850903"],"related_works":["https://openalex.org/W2021595906","https://openalex.org/W2012531322","https://openalex.org/W2402761219","https://openalex.org/W2766087987","https://openalex.org/W1606020025","https://openalex.org/W2785900585","https://openalex.org/W2353730437","https://openalex.org/W106304674","https://openalex.org/W2095992409","https://openalex.org/W2490303674"],"abstract_inverted_index":{"While":[0],"much":[1],"of":[2,73,102],"modern":[3],"speech":[4],"and":[5,91,100,107],"audio":[6,16,86],"processing":[7],"relies":[8],"on":[9,37,84],"deep":[10],"neural":[11],"networks":[12],"trained":[13],"using":[14,47,80],"fixed":[15],"representations,":[17],"recent":[18],"studies":[19,41],"suggest":[20],"great":[21],"potential":[22],"in":[23,45],"acoustic":[24],"frontends":[25,46],"learnt":[26],"jointly":[27],"with":[28],"a":[29,52,66,74,140],"backend.":[30],"In":[31],"this":[32],"study,":[33],"we":[34,69],"focus":[35],"specifically":[36],"learnable":[38,48,75,141],"filterbanks.":[39],"Prior":[40],"have":[42],"reported":[43],"that":[44,112,134],"filterbanks":[49,119],"initialised":[50,131],"to":[51,77,123,143],"mel":[53],"scale,":[54],"the":[55,71,97,103,118],"learned":[56,104],"filters":[57,105],"do":[58],"not":[59],"differ":[60],"substantially":[61],"from":[62,130],"their":[63,124],"initialisation.":[64],"Using":[65],"Gabor-based":[67],"filterbank,":[68],"investigate":[70],"sensitivity":[72,122],"filterbank":[76],"its":[78],"initialisation":[79,82,125],"several":[81],"strategies":[83,137],"two":[85],"tasks:":[87],"voice":[88],"activity":[89],"detection":[90],"bird":[92],"species":[93],"identification.":[94],"We":[95,110],"use":[96],"Jensen-Shannon":[98],"Distance":[99],"analysis":[101],"before":[106],"after":[108],"training.":[109],"show":[111],"although":[113],"performance":[114],"is":[115],"overall":[116,146],"improved,":[117],"exhibit":[120],"strong":[121],"strategy.":[126],"The":[127],"limited":[128],"movement":[129],"values":[132],"suggests":[133],"alternate":[135],"optimisation":[136],"may":[138],"allow":[139],"frontend":[142],"reach":[144],"better":[145],"performance.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}