{"id":"https://openalex.org/W3015724290","doi":"https://doi.org/10.1109/icassp40776.2020.9053934","title":"Time-Domain Audio Source Separation Based on Wave-U-Net Combined with Discrete Wavelet Transform","display_name":"Time-Domain Audio Source Separation Based on Wave-U-Net Combined with Discrete Wavelet Transform","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015724290","doi":"https://doi.org/10.1109/icassp40776.2020.9053934","mag":"3015724290"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/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, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The 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, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102941659"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":1.6725,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.84333029,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"386","last_page":"390"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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":0.9980000257492065,"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":0.8650096654891968},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6617769002914429},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6575149893760681},{"id":"https://openalex.org/keywords/anti-aliasing","display_name":"Anti-aliasing","score":0.5857307314872742},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5842927098274231},{"id":"https://openalex.org/keywords/discrete-wavelet-transform","display_name":"Discrete wavelet transform","score":0.5794987082481384},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.538413941860199},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.5353062152862549},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.4911136329174042},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4893738627433777},{"id":"https://openalex.org/keywords/wavelet-packet-decomposition","display_name":"Wavelet packet decomposition","score":0.4738976061344147},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.46489399671554565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4524111747741699},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.4442480802536011},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4387713372707367},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.4176263213157654},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.39742809534072876},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3855949342250824},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3219863176345825},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.27010026574134827},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.22081351280212402},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.1608651578426361},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.12487277388572693}],"concepts":[{"id":"https://openalex.org/C4069607","wikidata":"https://www.wikidata.org/wiki/Q868732","display_name":"Aliasing","level":3,"score":0.8650096654891968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6617769002914429},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6575149893760681},{"id":"https://openalex.org/C534633266","wikidata":"https://www.wikidata.org/wiki/Q4774317","display_name":"Anti-aliasing","level":5,"score":0.5857307314872742},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5842927098274231},{"id":"https://openalex.org/C46286280","wikidata":"https://www.wikidata.org/wiki/Q2414958","display_name":"Discrete wavelet transform","level":4,"score":0.5794987082481384},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.538413941860199},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.5353062152862549},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.4911136329174042},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4893738627433777},{"id":"https://openalex.org/C155777637","wikidata":"https://www.wikidata.org/wiki/Q2736187","display_name":"Wavelet packet decomposition","level":4,"score":0.4738976061344147},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.46489399671554565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4524111747741699},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4442480802536011},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4387713372707367},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.4176263213157654},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.39742809534072876},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3855949342250824},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3219863176345825},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.27010026574134827},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.22081351280212402},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.1608651578426361},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.12487277388572693},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.75,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1849277567","https://openalex.org/W1901129140","https://openalex.org/W2020919250","https://openalex.org/W2117188745","https://openalex.org/W2120847449","https://openalex.org/W2123872146","https://openalex.org/W2132984323","https://openalex.org/W2221409856","https://openalex.org/W2401387233","https://openalex.org/W2774707525","https://openalex.org/W2786128974","https://openalex.org/W2889424860","https://openalex.org/W2898963093","https://openalex.org/W2900132857","https://openalex.org/W2913314773","https://openalex.org/W2949578333","https://openalex.org/W2952218014","https://openalex.org/W2962695743","https://openalex.org/W2963443859","https://openalex.org/W2963452667","https://openalex.org/W2963750251","https://openalex.org/W2963751183","https://openalex.org/W2963992487","https://openalex.org/W2972653970","https://openalex.org/W2998657200","https://openalex.org/W3099330747","https://openalex.org/W4297798428","https://openalex.org/W4298310324","https://openalex.org/W6639204139","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/W2379888591","https://openalex.org/W2087912877","https://openalex.org/W2391609463","https://openalex.org/W2387218911","https://openalex.org/W2013059460","https://openalex.org/W2389475303","https://openalex.org/W2016506074","https://openalex.org/W2130372912","https://openalex.org/W296586643","https://openalex.org/W1965744692"],"abstract_inverted_index":{"We":[0,43],"propose":[1],"a":[2,17,84],"time-domain":[3],"audio":[4],"source":[5,87,127],"separation":[6,88,128],"method":[7,24,135],"using":[8],"down-sampling":[9],"(DS)":[10],"and":[11,39,53,63,114,136,145],"up-sampling":[12],"(US)":[13],"layers":[14,58,94],"based":[15,26],"on":[16,27,104,125],"discrete":[18],"wavelet":[19],"transform":[20],"(DWT).":[21],"The":[22],"proposed":[23,122,134],"is":[25],"one":[28],"of":[29,50,59,74,96,132,139],"the":[30,56,69,72,98,105,108,115,121,130,133,137,142,146],"state-of-the-art":[31],"deep":[32],"neural":[33],"networks,":[34],"Wave-U-Net,":[35],"which":[36],"successively":[37],"down-samples":[38],"up-samples":[40],"feature":[41],"maps.":[42],"find":[44],"that":[45,49,55,107],"this":[46,101],"architecture":[47],"resembles":[48],"multiresolution":[51],"analysis,":[52],"reveal":[54],"DS":[57,93],"Wave-U-Net":[60],"cause":[61],"aliasing":[62],"may":[64,77],"discard":[65],"information":[66],"useful":[67],"for":[68],"separation.":[70],"Although":[71],"effects":[73],"these":[75],"problems":[76],"be":[78],"reduced":[79],"by":[80],"training,":[81],"to":[82],"achieve":[83],"more":[85],"reliable":[86],"method,":[89],"we":[90,119],"should":[91],"design":[92,120],"capable":[95],"overcoming":[97],"problems.":[99],"With":[100],"belief,":[102],"focusing":[103],"fact":[106],"DWT":[109],"has":[110],"an":[111],"anti-aliasing":[112,143],"filter":[113],"perfect":[116,147],"reconstruction":[117,148],"property,":[118],"layers.":[123],"Experiments":[124],"music":[126],"show":[129],"efficacy":[131],"importance":[138],"simultaneously":[140],"considering":[141],"filters":[144],"property.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}