{"id":"https://openalex.org/W4221161923","doi":"https://doi.org/10.21437/interspeech.2022-249","title":"SepTr: Separable Transformer for Audio Spectrogram Processing","display_name":"SepTr: Separable Transformer for Audio Spectrogram Processing","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4221161923","doi":"https://doi.org/10.21437/interspeech.2022-249"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-249","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-249","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.09581","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083932459","display_name":"Nicolae-C\u0103t\u0103lin Ristea","orcid":"https://orcid.org/0000-0002-7880-9307"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nicolaea Catalin Ristea","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081017623","display_name":"Radu Tudor Ionescu","orcid":"https://orcid.org/0000-0002-9301-1950"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Radu Tudor Ionescu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Fahad Shahbaz Khan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fahad Shahbaz Khan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083932459"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2431,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.34246144,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4103","last_page":"4107"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.22439999878406525,"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":0.22439999878406525,"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":0.13930000364780426,"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/T11034","display_name":"Digital Filter Design and Implementation","score":0.08569999784231186,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8305050134658813},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7021267414093018},{"id":"https://openalex.org/keywords/separable-space","display_name":"Separable space","score":0.6053290963172913},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.602496325969696},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.43934327363967896},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.371776819229126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3692673444747925},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32928305864334106},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21212536096572876},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1811477243900299},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1437743902206421}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8305050134658813},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7021267414093018},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.6053290963172913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.602496325969696},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.43934327363967896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.371776819229126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3692673444747925},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32928305864334106},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21212536096572876},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1811477243900299},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1437743902206421},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2022-249","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-249","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2203.09581","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.09581","pdf_url":"https://arxiv.org/pdf/2203.09581","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2203.09581","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.09581","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.09581","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.09581","pdf_url":"https://arxiv.org/pdf/2203.09581","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5937815900","display_name":null,"funder_award_id":"PN-III-P1-1.1-TE-2019-0235","funder_id":"https://openalex.org/F4320323983","funder_display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii"},{"id":"https://openalex.org/G6058054535","display_name":null,"funder_award_id":"PN-III-P1-1.1","funder_id":"https://openalex.org/F4320323983","funder_display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii"},{"id":"https://openalex.org/G7430875941","display_name":null,"funder_award_id":"grant","funder_id":"https://openalex.org/F4320323983","funder_display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii"},{"id":"https://openalex.org/G7688415803","display_name":null,"funder_award_id":"PN-III-P1-1","funder_id":"https://openalex.org/F4320323983","funder_display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii"},{"id":"https://openalex.org/G8141067265","display_name":null,"funder_award_id":"PNCDI III","funder_id":"https://openalex.org/F4320323983","funder_display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii"}],"funders":[{"id":"https://openalex.org/F4320323983","display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii","ror":"https://ror.org/01q7jq182"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4221161923.pdf","grobid_xml":"https://content.openalex.org/works/W4221161923.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W11543369","https://openalex.org/W8831803","https://openalex.org/W2723084","https://openalex.org/W1770742","https://openalex.org/W15731617","https://openalex.org/W587461","https://openalex.org/W8026701","https://openalex.org/W17822742","https://openalex.org/W10113152","https://openalex.org/W1061142"],"abstract_inverted_index":{"Following":[0],"the":[1,16,19,56,74,85,100,106,111,117,148,154],"successful":[2],"application":[3],"of":[4,18,150],"vision":[5,10,45,136],"transformers":[6,50,137],"in":[7,96],"multiple":[8],"computer":[9],"tasks,":[11],"these":[12],"models":[13],"have":[14],"drawn":[15],"attention":[17,75],"signal":[20],"processing":[21],"community.":[22],"This":[23],"is":[24,53,71,165],"because":[25],"signals":[26],"are":[27],"often":[28],"represented":[29],"as":[30,42,167],"spectrograms":[31,52],"(e.g.":[32],"through":[33],"Discrete":[34],"Fourier":[35],"Transform)":[36],"which":[37],"can":[38],"be":[39],"directly":[40],"provided":[41],"input":[43,155],"to":[44,51,72,77,103,114],"transformers.":[46],"However,":[47],"naively":[48],"applying":[49],"suboptimal.":[54],"Since":[55],"axes":[57],"represent":[58],"distinct":[59],"dimensions,":[60],"i.e.":[61],"frequency":[62,119],"and":[63,110,138],"time,":[64],"we":[65,83],"argue":[66],"that":[67,91,130],"a":[68,97,159],"better":[69],"approach":[70],"separate":[73],"dedicated":[76],"each":[78],"axis.":[79],"To":[80],"this":[81],"end,":[82],"propose":[84],"Separable":[86],"Transformer":[87],"(SepTr),":[88],"an":[89],"architecture":[90,133],"employs":[92],"two":[93],"transformer":[94],"blocks":[95],"sequential":[98],"manner,":[99],"first":[101],"attending":[102,113],"tokens":[104,115],"within":[105,116],"same":[107,118],"time":[108],"interval,":[109],"second":[112],"bin.":[120],"We":[121],"conduct":[122],"experiments":[123],"on":[124],"three":[125],"benchmark":[126],"data":[127],"sets,":[128],"showing":[129],"our":[131],"separable":[132],"outperforms":[134],"conventional":[135],"other":[139],"state-of-the-art":[140],"methods.":[141],"Unlike":[142],"standard":[143],"transformers,":[144],"SepTr":[145],"linearly":[146],"scales":[147],"number":[149],"trainable":[151],"parameters":[152],"with":[153],"size,":[156],"thus":[157],"having":[158],"lower":[160],"memory":[161],"footprint.":[162],"Our":[163],"code":[164],"available":[166],"open":[168],"source":[169],"at":[170],"https://github.com/ristea/septr.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2022-04-03T00:00:00"}