{"id":"https://openalex.org/W2927999579","doi":"https://doi.org/10.1109/jstsp.2019.2908696","title":"TimeScaleNet: A Multiresolution Approach for Raw Audio Recognition Using Learnable Biquadratic IIR Filters and Residual Networks of Depthwise-Separable One-Dimensional Atrous Convolutions","display_name":"TimeScaleNet: A Multiresolution Approach for Raw Audio Recognition Using Learnable Biquadratic IIR Filters and Residual Networks of Depthwise-Separable One-Dimensional Atrous Convolutions","publication_year":2019,"publication_date":"2019-04-01","ids":{"openalex":"https://openalex.org/W2927999579","doi":"https://doi.org/10.1109/jstsp.2019.2908696","mag":"2927999579"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2019.2908696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2019.2908696","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5006258841","display_name":"\u00c9ric Bavu","orcid":"https://orcid.org/0000-0001-6395-634X"},"institutions":[{"id":"https://openalex.org/I124158823","display_name":"Conservatoire National des Arts et M\u00e9tiers","ror":"https://ror.org/0175hh227","country_code":"FR","type":"education","lineage":["https://openalex.org/I124158823","https://openalex.org/I4210134562"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Eric Bavu","raw_affiliation_strings":["Laboratoire de M\u00e9canique des Structures et des Syst\u00e8mes Coupl\u00e9s, Conservatoire National des Arts et M\u00e9tiers, Paris, France","LMSSC - Laboratoire de M\u00e9canique des Structures et des Syst\u00e8mes Coupl\u00e9s (292, rue Saint Martin 75141 PARIS Cedex 03 - France)"],"raw_orcid":"https://orcid.org/0000-0001-6395-634X","affiliations":[{"raw_affiliation_string":"Laboratoire de M\u00e9canique des Structures et des Syst\u00e8mes Coupl\u00e9s, Conservatoire National des Arts et M\u00e9tiers, Paris, France","institution_ids":["https://openalex.org/I124158823"]},{"raw_affiliation_string":"LMSSC - Laboratoire de M\u00e9canique des Structures et des Syst\u00e8mes Coupl\u00e9s (292, rue Saint Martin 75141 PARIS Cedex 03 - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040694178","display_name":"Aro Ramamonjy","orcid":null},"institutions":[{"id":"https://openalex.org/I124158823","display_name":"Conservatoire National des Arts et M\u00e9tiers","ror":"https://ror.org/0175hh227","country_code":"FR","type":"education","lineage":["https://openalex.org/I124158823","https://openalex.org/I4210134562"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Aro Ramamonjy","raw_affiliation_strings":["Laboratoire de M\u00e9canique des Structures et des Syst\u00e8mes Coupl\u00e9s, Conservatoire National des Arts et M\u00e9tiers, Paris, France","LMSSC - Laboratoire de M\u00e9canique des Structures et des Syst\u00e8mes Coupl\u00e9s (292, rue Saint Martin 75141 PARIS Cedex 03 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire de M\u00e9canique des Structures et des Syst\u00e8mes Coupl\u00e9s, Conservatoire National des Arts et M\u00e9tiers, Paris, France","institution_ids":["https://openalex.org/I124158823"]},{"raw_affiliation_string":"LMSSC - Laboratoire de M\u00e9canique des Structures et des Syst\u00e8mes Coupl\u00e9s (292, rue Saint Martin 75141 PARIS Cedex 03 - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032227336","display_name":"Hadrien Pujol","orcid":null},"institutions":[{"id":"https://openalex.org/I124158823","display_name":"Conservatoire National des Arts et M\u00e9tiers","ror":"https://ror.org/0175hh227","country_code":"FR","type":"education","lineage":["https://openalex.org/I124158823","https://openalex.org/I4210134562"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Hadrien Pujol","raw_affiliation_strings":["Laboratoire de M\u00e9canique des Structures et des Syst\u00e8mes Coupl\u00e9s, Conservatoire National des Arts et M\u00e9tiers, Paris, France","LMSSC - Laboratoire de M\u00e9canique des Structures et des Syst\u00e8mes Coupl\u00e9s (292, rue Saint Martin 75141 PARIS Cedex 03 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire de M\u00e9canique des Structures et des Syst\u00e8mes Coupl\u00e9s, Conservatoire National des Arts et M\u00e9tiers, Paris, France","institution_ids":["https://openalex.org/I124158823"]},{"raw_affiliation_string":"LMSSC - Laboratoire de M\u00e9canique des Structures et des Syst\u00e8mes Coupl\u00e9s (292, rue Saint Martin 75141 PARIS Cedex 03 - France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057486415","display_name":"Alexandre Garcia","orcid":"https://orcid.org/0000-0002-8479-4199"},"institutions":[{"id":"https://openalex.org/I124158823","display_name":"Conservatoire National des Arts et M\u00e9tiers","ror":"https://ror.org/0175hh227","country_code":"FR","type":"education","lineage":["https://openalex.org/I124158823","https://openalex.org/I4210134562"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alexandre Garcia","raw_affiliation_strings":["Laboratoire de M\u00e9canique des Structures et des Syst\u00e8mes Coupl\u00e9s, Conservatoire National des Arts et M\u00e9tiers, Paris, France","LMSSC - Laboratoire de M\u00e9canique des Structures et des Syst\u00e8mes Coupl\u00e9s (292, rue Saint Martin 75141 PARIS Cedex 03 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire de M\u00e9canique des Structures et des Syst\u00e8mes Coupl\u00e9s, Conservatoire National des Arts et M\u00e9tiers, Paris, France","institution_ids":["https://openalex.org/I124158823"]},{"raw_affiliation_string":"LMSSC - Laboratoire de M\u00e9canique des Structures et des Syst\u00e8mes Coupl\u00e9s (292, rue Saint Martin 75141 PARIS Cedex 03 - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8345,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.71860734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"13","issue":"2","first_page":"220","last_page":"235"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9979000091552734,"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/filter-bank","display_name":"Filter bank","score":0.7061520218849182},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6651799082756042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5561067461967468},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5538080930709839},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5277296304702759},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5201711654663086},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5159714818000793},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5126756429672241},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.5101876258850098},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.41963934898376465},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.41477733850479126},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2422737181186676},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1932227611541748}],"concepts":[{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.7061520218849182},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6651799082756042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5561067461967468},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5538080930709839},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5277296304702759},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5201711654663086},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5159714818000793},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5126756429672241},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.5101876258850098},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.41963934898376465},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.41477733850479126},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2422737181186676},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1932227611541748},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstsp.2019.2908696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2019.2908696","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-02088214v1","is_oa":false,"landing_page_url":"https://hal.science/hal-02088214","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://ieeexplore.ieee.org/document/8678740","raw_type":"Journal articles"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W608300865","https://openalex.org/W1489184006","https://openalex.org/W1498436455","https://openalex.org/W1501987291","https://openalex.org/W1522301498","https://openalex.org/W1542280630","https://openalex.org/W1578856370","https://openalex.org/W1677182931","https://openalex.org/W1836465849","https://openalex.org/W1847088711","https://openalex.org/W1972567154","https://openalex.org/W2050758723","https://openalex.org/W2052666245","https://openalex.org/W2059652044","https://openalex.org/W2060539877","https://openalex.org/W2064675550","https://openalex.org/W2070696251","https://openalex.org/W2076105648","https://openalex.org/W2090431713","https://openalex.org/W2090861223","https://openalex.org/W2097117768","https://openalex.org/W2097772361","https://openalex.org/W2130380490","https://openalex.org/W2160815625","https://openalex.org/W2170505850","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2343218625","https://openalex.org/W2398826216","https://openalex.org/W2407023693","https://openalex.org/W2408093180","https://openalex.org/W2509065397","https://openalex.org/W2512499206","https://openalex.org/W2519091744","https://openalex.org/W2529337537","https://openalex.org/W2588610957","https://openalex.org/W2589857635","https://openalex.org/W2591013610","https://openalex.org/W2592168896","https://openalex.org/W2769912137","https://openalex.org/W2782526840","https://openalex.org/W2794150026","https://openalex.org/W2797583228","https://openalex.org/W2883588054","https://openalex.org/W2905477978","https://openalex.org/W2950621961","https://openalex.org/W2951920181","https://openalex.org/W2953333557","https://openalex.org/W2953384591","https://openalex.org/W2962785008","https://openalex.org/W2962949994","https://openalex.org/W2963103134","https://openalex.org/W2963451564","https://openalex.org/W2963454111","https://openalex.org/W2964187693","https://openalex.org/W2970717128","https://openalex.org/W3098357269","https://openalex.org/W3105202226","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6638824847","https://openalex.org/W6698183232","https://openalex.org/W6712560600","https://openalex.org/W6713134421","https://openalex.org/W6714171909","https://openalex.org/W6733590821","https://openalex.org/W6739879593","https://openalex.org/W6746451879","https://openalex.org/W6750665317","https://openalex.org/W6765069029","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W4388685194","https://openalex.org/W4312407344","https://openalex.org/W2894289927"],"abstract_inverted_index":{"In":[0,71],"this":[1],"paper,":[2],"we":[3],"show":[4],"the":[5,16,41,46,56,59,119,163,167,177,190,195,239],"benefit":[6],"of":[7,32,58,79,147,155,179,204,225],"a":[8,33,76,98,112,126,144,200,221],"multi-resolution":[9],"approach":[10,51],"that":[11,116],"allows":[12,52,108],"us":[13,53,109],"to":[14,54,110,118],"encode":[15],"relevant":[17],"information":[18],"contained":[19],"in":[20,170,176],"unprocessed":[21],"time-domain":[22],"acoustic":[23],"signals.":[24],"TimeScaleNet":[25,185],"aims":[26,157],"at":[27,40,45,158,166],"learning":[28,36,60,66],"an":[29],"efficient":[30],"representation":[31],"sound,":[34],"by":[35,62],"time":[37,164],"dependencies":[38],"both":[39,188],"sample":[42],"level":[43],"and":[44,67,123,130,194,220],"frame":[47,168],"level.":[48],"The":[49,105,135],"proposed":[50],"improve":[55],"interpretability":[57],"scheme,":[61],"unifying":[63],"advanced":[64],"deep":[65],"signal":[68,92],"processing":[69],"techniques.":[70],"particular,":[72],"TimeScaleNet's":[73],"architecture":[74],"introduces":[75],"new":[77],"form":[78],"recurrent":[80],"neural":[81],"layer,":[82],"which":[83],"is":[84,140,186],"directly":[85],"inspired":[86],"from":[87],"digital":[88,102],"infinite":[89],"impulse-response":[90],"(IIR)":[91],"processing.":[93],"This":[94,152],"layer":[95],"acts":[96],"as":[97],"learnable":[99,106,133],"passband":[100],"biquadratic":[101],"IIR":[103],"filterbank.":[104],"filterbank":[107],"build":[111],"time-frequency-like":[113],"feature":[114,138],"map":[115,139],"self-adapts":[117],"specific":[120],"recognition":[121],"task":[122],"dataset,":[124],"with":[125],"large":[127],"receptive":[128],"field":[129],"very":[131],"few":[132],"parameters.":[134],"obtained":[136],"frame-level":[137],"then":[141],"processed":[142],"using":[143,189],"residual":[145],"network":[146],"depthwise":[148],"separable":[149],"atrous":[150],"convolutions.":[151],"second":[153],"scale":[154],"analysis":[156],"efficiently":[159],"encoding":[160],"relationships":[161],"between":[162],"fluctuations":[165],"timescale,":[169],"different":[171],"learnt":[172],"pooled":[173],"frequency":[174],"bands,":[175],"range":[178],"[20":[180],"ms":[181],";":[182],"200":[183],"ms].":[184],"tested":[187],"Speech":[191],"Commands":[192],"Dataset":[193],"ESC-10":[196],"Dataset.":[197],"We":[198],"report":[199],"high":[201],"mean":[202],"accuracy":[203,224],"$94.87":[205],"\\pm":[206,214,227,235],"0.24":[207,215],"\\%$":[208,229],"(macro":[209,230],"averaged":[210,231],"F1-score":[211,232],":":[212,233],"$94.9":[213],"\\%$)":[216,237],"for":[217,238],"speech":[218],"recognition,":[219],"rather":[222],"moderate":[223],"$69.71":[226],"1.91":[228],"$70.14":[234],"1.57":[236],"environmental":[240],"sound":[241],"classification":[242],"task.":[243]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}