{"id":"https://openalex.org/W4372349759","doi":"https://doi.org/10.1109/icassp49357.2023.10095171","title":"A Content Adaptive Learnable \"Time-Frequency\" Representation for audio Signal Processing","display_name":"A Content Adaptive Learnable \"Time-Frequency\" Representation for audio Signal Processing","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372349759","doi":"https://doi.org/10.1109/icassp49357.2023.10095171"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095171","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095171","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/A5017296738","display_name":"Prateek Verma","orcid":"https://orcid.org/0000-0002-6402-8948"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prateek Verma","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088100932","display_name":"Chris Chafe","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Chafe","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.2417,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.37687441,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"29","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":0.9997000098228455,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8110103607177734},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6922674775123596},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.5532952547073364},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.539313793182373},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.535595178604126},{"id":"https://openalex.org/keywords/finite-impulse-response","display_name":"Finite impulse response","score":0.5290067791938782},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5252817869186401},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.437261164188385},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.43492603302001953},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.42025241255760193},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.41622117161750793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3762974143028259},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2990402281284332},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.29706889390945435},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.20226740837097168},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.18758121132850647},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.09827873110771179},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0964718759059906},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07853513956069946}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8110103607177734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6922674775123596},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.5532952547073364},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.539313793182373},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.535595178604126},{"id":"https://openalex.org/C198386975","wikidata":"https://www.wikidata.org/wiki/Q117785","display_name":"Finite impulse response","level":2,"score":0.5290067791938782},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5252817869186401},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.437261164188385},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.43492603302001953},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.42025241255760193},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.41622117161750793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3762974143028259},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2990402281284332},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.29706889390945435},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.20226740837097168},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.18758121132850647},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.09827873110771179},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0964718759059906},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07853513956069946},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095171","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095171","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1571821784","https://openalex.org/W2150884987","https://openalex.org/W2398826216","https://openalex.org/W2516301810","https://openalex.org/W2547875792","https://openalex.org/W2593116425","https://openalex.org/W2606176153","https://openalex.org/W2752796333","https://openalex.org/W2794753807","https://openalex.org/W2795109282","https://openalex.org/W2916113431","https://openalex.org/W2963011080","https://openalex.org/W2963425185","https://openalex.org/W2963799213","https://openalex.org/W3005680577","https://openalex.org/W3093494400","https://openalex.org/W3134307371","https://openalex.org/W3134486096","https://openalex.org/W3154596443","https://openalex.org/W3174290991","https://openalex.org/W3205743929","https://openalex.org/W3210574093","https://openalex.org/W4205689591","https://openalex.org/W4286987939","https://openalex.org/W4287372095","https://openalex.org/W4287802874","https://openalex.org/W4293665662","https://openalex.org/W4293718192","https://openalex.org/W4295731579","https://openalex.org/W4301107988","https://openalex.org/W4385245566","https://openalex.org/W6634082615","https://openalex.org/W6729448088","https://openalex.org/W6729831399","https://openalex.org/W6732520560","https://openalex.org/W6736723571","https://openalex.org/W6739901393","https://openalex.org/W6747635987","https://openalex.org/W6774314701","https://openalex.org/W6776218486","https://openalex.org/W6783462664","https://openalex.org/W6784559596","https://openalex.org/W6789403026","https://openalex.org/W6791141078","https://openalex.org/W6791429434","https://openalex.org/W6793736971","https://openalex.org/W6800875267"],"related_works":["https://openalex.org/W2327143552","https://openalex.org/W2085219086","https://openalex.org/W2141599702","https://openalex.org/W2188078572","https://openalex.org/W4360764600","https://openalex.org/W2289868279","https://openalex.org/W2793814466","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293"],"abstract_inverted_index":{"We":[0,120],"propose":[1,110],"a":[2,45,48,87,95,103,111,115,126,133,141],"learnable":[3,49,117,167],"content":[4,160],"adaptive":[5],"front":[6,50],"end":[7],"for":[8,70],"audio":[9,123],"signal":[10,124,151],"processing.":[11],"Before":[12],"the":[13,56,62,71,77,149,153,159,162,176],"modern":[14],"advent":[15],"of":[16,58,74,113,128,143,161],"deep":[17],"learning,":[18],"we":[19,109],"used":[20],"fixed":[21],"representation":[22,169],"non-learnable":[23],"front-ends":[24],"like":[25],"spectrogram":[26],"or":[27],"mel-spectrogram":[28],"with/without":[29],"neural":[30],"architectures.":[31],"With":[32,76],"convolutional":[33,84,129],"architectures":[34,81],"supporting":[35],"various":[36],"applications":[37],"such":[38],"as":[39],"ASR":[40],"and":[41,61,68,147],"acoustic":[42],"scene":[43],"understanding,":[44],"shift":[46,78],"to":[47,79,102,139],"ends":[51],"occurred":[52],"in":[53,178],"which":[54],"both":[55],"type":[57],"basis":[59],"functions":[60],"weight":[63],"were":[64],"learned":[65],"from":[66],"scratch":[67],"optimized":[69],"particular":[72],"task":[73],"interest.":[75],"transformer-based":[80],"with":[82],"no":[83],"blocks":[85],"present,":[86],"linear":[88],"layer":[89],"projects":[90],"small":[91,96],"waveform":[92],"patches":[93],"onto":[94],"latent":[97],"dimension":[98],"before":[99],"feeding":[100],"them":[101],"transformer":[104],"architecture.":[105],"In":[106],"this":[107,179],"work,":[108],"way":[112],"computing":[114],"content-adaptive":[116,166],"time-frequency":[118,168],"representation.":[119],"pass":[121],"each":[122,131],"through":[125,152],"bank":[127,142,156],"filters,":[130],"giving":[132],"fixed-dimensional":[134],"vector.":[135],"It":[136],"is":[137],"akin":[138],"learning":[140],"finite":[144],"impulse-response":[145],"filterbanks":[146],"passing":[148],"input":[150,163],"optimum":[154],"filter":[155],"depending":[157],"on":[158],"signal.":[164],"A":[165],"may":[170],"be":[171],"more":[172],"broadly":[173],"applicable,":[174],"beyond":[175],"experiments":[177],"paper.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}