{"id":"https://openalex.org/W4294310886","doi":"https://doi.org/10.1109/taslp.2022.3203907","title":"Sampling-Frequency-Independent Convolutional Layer and its Application to Audio Source Separation","display_name":"Sampling-Frequency-Independent Convolutional Layer and its Application to Audio Source Separation","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4294310886","doi":"https://doi.org/10.1109/taslp.2022.3203907"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3203907","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3203907","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/taslp.2022.3203907","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102972958","display_name":"Koichi Saito","orcid":"https://orcid.org/0000-0002-8563-9262"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Koichi Saito","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102941659","display_name":"Tomohiko Nakamura","orcid":"https://orcid.org/0000-0003-4385-7170"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiko Nakamura","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4385-7170","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034837951","display_name":"Kohei Yatabe","orcid":"https://orcid.org/0000-0002-1345-0663"},"institutions":[{"id":"https://openalex.org/I92614990","display_name":"Tokyo University of Agriculture and Technology","ror":"https://ror.org/00qg0kr10","country_code":"JP","type":"education","lineage":["https://openalex.org/I92614990"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kohei Yatabe","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Tokyo University of Agriculture and Technology, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-1345-0663","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Tokyo University of Agriculture and Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I92614990"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-0876-5617","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102972958"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":1.9343,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85923949,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"2928","last_page":"2943"},"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":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/T11447","display_name":"Blind Source Separation Techniques","score":0.996999979019165,"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/computer-science","display_name":"Computer science","score":0.7542054653167725},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.7085832953453064},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6376872062683105},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6157371997833252},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.48021969199180603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4606144428253174},{"id":"https://openalex.org/keywords/decimation","display_name":"Decimation","score":0.4582824110984802},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.41938111186027527},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41080474853515625},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4092192053794861},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11513277888298035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7542054653167725},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.7085832953453064},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6376872062683105},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6157371997833252},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.48021969199180603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4606144428253174},{"id":"https://openalex.org/C173642442","wikidata":"https://www.wikidata.org/wiki/Q1253346","display_name":"Decimation","level":3,"score":0.4582824110984802},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.41938111186027527},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41080474853515625},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4092192053794861},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11513277888298035},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3203907","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3203907","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2022.3203907","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3203907","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1849277567","https://openalex.org/W2050758723","https://openalex.org/W2101926813","https://openalex.org/W2127851351","https://openalex.org/W2168249605","https://openalex.org/W2191779130","https://openalex.org/W2198584637","https://openalex.org/W2221409856","https://openalex.org/W2398826216","https://openalex.org/W2889424860","https://openalex.org/W2903502793","https://openalex.org/W2904310189","https://openalex.org/W2952218014","https://openalex.org/W2962901777","https://openalex.org/W2963122170","https://openalex.org/W2963751183","https://openalex.org/W2963992487","https://openalex.org/W2964052309","https://openalex.org/W2972411915","https://openalex.org/W2972653970","https://openalex.org/W2981976899","https://openalex.org/W2990594533","https://openalex.org/W2998657200","https://openalex.org/W3001377302","https://openalex.org/W3015199127","https://openalex.org/W3015247127","https://openalex.org/W3015360216","https://openalex.org/W3015753416","https://openalex.org/W3037149862","https://openalex.org/W3094893721","https://openalex.org/W3095263845","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3152594694","https://openalex.org/W3152620902","https://openalex.org/W3160191260","https://openalex.org/W3168997536","https://openalex.org/W3174280965","https://openalex.org/W3177067699","https://openalex.org/W3185109982","https://openalex.org/W3191469971","https://openalex.org/W4251033893","https://openalex.org/W4302296459","https://openalex.org/W6637151318","https://openalex.org/W6726497184","https://openalex.org/W6751512325","https://openalex.org/W6766196973","https://openalex.org/W6767164110","https://openalex.org/W6773772901","https://openalex.org/W6789403026"],"related_works":["https://openalex.org/W1524890377","https://openalex.org/W2340678901","https://openalex.org/W3029686646","https://openalex.org/W1513711368","https://openalex.org/W1526941731","https://openalex.org/W3106295919","https://openalex.org/W2355495591","https://openalex.org/W1551613892","https://openalex.org/W2863202953","https://openalex.org/W2049866946"],"abstract_inverted_index":{"Audio":[0],"source":[1,196,201],"separation":[2,197,202,211,225],"is":[3,18,44,49],"often":[4],"used":[5],"for":[6,79,87,180,217],"the":[7,35,40,52,58,63,115,162,177,207,231,243,253],"preprocessing":[8],"of":[9,14,30,34,39,83,106,114,132,157,193,246],"various":[10,108,181],"tasks,":[11],"and":[12,135,154,168,223],"one":[13],"its":[15],"ultimate":[16],"goals":[17],"to":[19,213],"construct":[20,189],"a":[21,81,123,130,158,194,235],"single":[22],"versatile":[23,53],"preprocessor":[24,54],"that":[25,122,150,206,230],"can":[26,126,175],"handle":[27,56],"every":[28],"variety":[29,82],"audio":[31,42],"signal.":[32],"One":[33],"most":[36],"important":[37],"varieties":[38],"discrete-time":[41],"signal":[43,240],"sampling":[45,59,84,89,109,139,182,219,244,255],"frequency.":[46,140,256],"Since":[47],"it":[48],"usually":[50],"task-specific,":[51],"must":[55],"all":[57],"frequencies":[60,220,245],"required":[61],"by":[62],"possible":[64],"downstream":[65],"tasks.":[66],"However,":[67],"conventional":[68,195,236],"models":[69],"based":[70,238],"on":[71,138,239],"deep":[72],"neural":[73],"networks":[74,212],"(DNNs)":[75],"are":[76,249],"not":[77,93],"designed":[78],"handling":[80,107],"frequencies.":[85,110,183],"Thus,":[86],"unseen":[88,218],"frequencies,":[90],"they":[91],"may":[92],"work":[94,215],"appropriately.":[95],"In":[96],"this":[97,143],"paper,":[98],"we":[99,145,174,188,204],"propose":[100,146],"sampling-frequency-independent":[101],"(SFI)":[102],"convolutional":[103,124,159,178],"layers":[104,117,209],"capable":[105],"The":[111],"core":[112],"idea":[113],"proposed":[116,208,232],"comes":[118],"from":[119,161],"our":[120],"finding":[121],"layer":[125,160,179],"be":[127],"viewed":[128],"as":[129],"collection":[131],"digital":[133],"filters":[134,153],"inherently":[136],"depends":[137],"To":[141],"overcome":[142],"dependency,":[144],"an":[147,185,190],"SFI":[148,191],"structure":[149],"features":[151],"analog":[152,163],"generates":[155],"weights":[156],"filters.":[164],"By":[165],"utilizing":[166],"time-":[167],"frequency-domain":[169],"analog-to-digital":[170],"filter":[171],"conversion":[172],"techniques,":[173],"adapt":[176],"As":[184],"example":[186],"application,":[187],"version":[192],"network.":[198],"Through":[199],"music":[200],"experiments,":[203],"show":[205],"enable":[210],"consistently":[214],"well":[216],"in":[221],"objective":[222],"perceptual":[224],"qualities.":[226],"We":[227],"also":[228],"demonstrate":[229],"method":[233,237],"outperforms":[234],"resampling":[241],"when":[242],"input":[247],"signals":[248],"significantly":[250],"lower":[251],"than":[252],"trained":[254]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}