{"id":"https://openalex.org/W3152620902","doi":"https://doi.org/10.1109/taslp.2021.3072496","title":"Time-Domain Audio Source Separation With Neural Networks Based on Multiresolution Analysis","display_name":"Time-Domain Audio Source Separation With Neural Networks Based on Multiresolution Analysis","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3152620902","doi":"https://doi.org/10.1109/taslp.2021.3072496","mag":"3152620902"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3072496","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3072496","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9289074/09403999.pdf","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://ieeexplore.ieee.org/ielx7/6570655/9289074/09403999.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","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":true,"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/A5082488617","display_name":"Shihori Kozuka","orcid":"https://orcid.org/0009-0006-1923-0529"},"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":"Shihori Kozuka","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":"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":3,"corresponding_author_ids":["https://openalex.org/A5102941659"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":2.0048,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.86934707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"1687","last_page":"1701"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9969000220298767,"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/aliasing","display_name":"Aliasing","score":0.8660110831260681},{"id":"https://openalex.org/keywords/decimation","display_name":"Decimation","score":0.8091953992843628},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.708420991897583},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6373233795166016},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6286554336547852},{"id":"https://openalex.org/keywords/multiresolution-analysis","display_name":"Multiresolution analysis","score":0.6201616525650024},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5690882802009583},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.481243371963501},{"id":"https://openalex.org/keywords/anti-aliasing","display_name":"Anti-aliasing","score":0.45859068632125854},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4338027238845825},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4227229356765747},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.42130953073501587},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41083985567092896},{"id":"https://openalex.org/keywords/discrete-wavelet-transform","display_name":"Discrete wavelet transform","score":0.35118526220321655},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.30131208896636963},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.27825450897216797},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.26526403427124023},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.22179928421974182},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.1781603991985321},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.17339560389518738},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.07893642783164978}],"concepts":[{"id":"https://openalex.org/C4069607","wikidata":"https://www.wikidata.org/wiki/Q868732","display_name":"Aliasing","level":3,"score":0.8660110831260681},{"id":"https://openalex.org/C173642442","wikidata":"https://www.wikidata.org/wiki/Q1253346","display_name":"Decimation","level":3,"score":0.8091953992843628},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.708420991897583},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6373233795166016},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6286554336547852},{"id":"https://openalex.org/C121927907","wikidata":"https://www.wikidata.org/wiki/Q1952516","display_name":"Multiresolution analysis","level":5,"score":0.6201616525650024},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5690882802009583},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.481243371963501},{"id":"https://openalex.org/C534633266","wikidata":"https://www.wikidata.org/wiki/Q4774317","display_name":"Anti-aliasing","level":5,"score":0.45859068632125854},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4338027238845825},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4227229356765747},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.42130953073501587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41083985567092896},{"id":"https://openalex.org/C46286280","wikidata":"https://www.wikidata.org/wiki/Q2414958","display_name":"Discrete wavelet transform","level":4,"score":0.35118526220321655},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.30131208896636963},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27825450897216797},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.26526403427124023},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.22179928421974182},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.1781603991985321},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.17339560389518738},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.07893642783164978},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2021.3072496","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3072496","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9289074/09403999.pdf","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.2021.3072496","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3072496","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9289074/09403999.pdf","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":[{"id":"https://openalex.org/G1547730489","display_name":null,"funder_award_id":"JPJSBP120197203","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320315966","display_name":"Tateisi Science and Technology Foundation","ror":null},{"id":"https://openalex.org/F4320330014","display_name":"Kawai Foundation for Sound Technology and Music","ror":null},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3152620902.pdf","grobid_xml":"https://content.openalex.org/works/W3152620902.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1849277567","https://openalex.org/W1901129140","https://openalex.org/W2015370045","https://openalex.org/W2018735295","https://openalex.org/W2020919250","https://openalex.org/W2095665834","https://openalex.org/W2117188745","https://openalex.org/W2120847449","https://openalex.org/W2123872146","https://openalex.org/W2127851351","https://openalex.org/W2132984323","https://openalex.org/W2221409856","https://openalex.org/W2401387233","https://openalex.org/W2476548250","https://openalex.org/W2499905295","https://openalex.org/W2516594951","https://openalex.org/W2774707525","https://openalex.org/W2786128974","https://openalex.org/W2889424860","https://openalex.org/W2894785362","https://openalex.org/W2898963093","https://openalex.org/W2913314773","https://openalex.org/W2917831833","https://openalex.org/W2949578333","https://openalex.org/W2952218014","https://openalex.org/W2962695743","https://openalex.org/W2962949867","https://openalex.org/W2963443859","https://openalex.org/W2963452667","https://openalex.org/W2963543871","https://openalex.org/W2963750251","https://openalex.org/W2963751183","https://openalex.org/W2963992487","https://openalex.org/W2972653970","https://openalex.org/W2989528444","https://openalex.org/W2998657200","https://openalex.org/W2999669537","https://openalex.org/W3005363104","https://openalex.org/W3015360216","https://openalex.org/W3015724290","https://openalex.org/W3099330747","https://openalex.org/W3103301587","https://openalex.org/W4251101141","https://openalex.org/W4297798428","https://openalex.org/W4298310324","https://openalex.org/W6639824700","https://openalex.org/W6678131844","https://openalex.org/W6714644935","https://openalex.org/W6746914816","https://openalex.org/W6748455662","https://openalex.org/W6751512325","https://openalex.org/W6758857762","https://openalex.org/W6766320909"],"related_works":["https://openalex.org/W1652270319","https://openalex.org/W1914386603","https://openalex.org/W2379888591","https://openalex.org/W4313343711","https://openalex.org/W2391609463","https://openalex.org/W2387218911","https://openalex.org/W2050101570","https://openalex.org/W2389475303","https://openalex.org/W117470531","https://openalex.org/W2013059460"],"abstract_inverted_index":{"We":[0,153],"propose":[1],"a":[2,90,181],"time-domain":[3,30],"audio":[4],"source":[5,71,93,212],"separation":[6,72,94,213],"method":[7],"based":[8,24,130],"on":[9,25,111,131],"multiresolution":[10,15,124],"analysis,":[11,125],"which":[12,36,136],"we":[13,54,96,126,137,197,218],"call":[14,138],"deep":[16,31],"layered":[17],"analysis":[18],"(MRDLA).":[19],"The":[20],"MRDLA":[21],"model":[22],"is":[23],"one":[26],"of":[27,61,102,119,123,185,194,222,229],"the":[28,45,50,57,85,112,115,139,143,149,156,170,176,186,192,206,220,223,227,233,237],"state-of-the-art":[29],"neural":[32],"networks":[33],"(DNNs),":[34],"Wave-U-Net,":[35],"successively":[37],"down-samples":[38],"features":[39],"and":[40,65,148,226,236],"up-samples":[41],"them":[42],"to":[43,84,88,205],"have":[44,145],"original":[46],"time":[47],"resolution.":[48],"From":[49],"signal":[51],"processing":[52],"viewpoint,":[53],"found":[55],"that":[56,114,122,160],"down-sampling":[58],"(DS)":[59],"layers":[60,100,129,158,188],"Wave-U-Net":[62,120],"cause":[63],"aliasing":[64],"may":[66],"discard":[67],"information":[68],"useful":[69],"for":[70,200],"because":[73,142],"they":[74],"are":[75,82],"implemented":[76],"with":[77,169],"decimation.":[78],"These":[79],"two":[80],"problems":[81],"due":[83],"decimation;":[86],"thus,":[87],"achieve":[89],"more":[91],"reliable":[92],"method,":[95],"should":[97],"design":[98],"DS":[99,117,128],"capable":[101],"simultaneously":[103,230],"overcoming":[104],"these":[105],"problems.":[106],"With":[107],"this":[108,201],"motivation,":[109],"focusing":[110],"fact":[113],"successive":[116],"architecture":[118],"resembles":[121],"develop":[127],"discrete":[132],"wavelet":[133,162],"transforms":[134],"(DWTs),":[135],"DWT":[140,157,187],"layers,":[141],"DWTs":[144],"anti-aliasing":[146,195,234],"filters":[147,235],"perfect":[150,177,207,238],"reconstruction":[151,178,208,239],"property.":[152,179,209,240],"further":[154],"extend":[155],"such":[159],"their":[161],"basis":[163],"functions":[164],"can":[165],"be":[166],"trained":[167],"together":[168],"other":[171],"DNN":[172],"components":[173],"while":[174],"maintaining":[175],"Since":[180],"straightforward":[182],"trainable":[183],"extension":[184],"does":[189],"not":[190],"guarantee":[191,202],"existence":[193],"filters,":[196],"derive":[198],"constraints":[199],"in":[203],"addition":[204],"Through":[210],"music":[211],"experiments":[214],"including":[215],"subjective":[216],"evaluations,":[217],"show":[219],"efficacy":[221],"proposed":[224],"methods":[225],"importance":[228],"considering":[231],"both":[232]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}