{"id":"https://openalex.org/W4285108271","doi":"https://doi.org/10.1109/lsp.2022.3187316","title":"Hierarchic Temporal Convolutional Network With Cross-Domain Encoder for Music Source Separation","display_name":"Hierarchic Temporal Convolutional Network With Cross-Domain Encoder for Music Source Separation","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285108271","doi":"https://doi.org/10.1109/lsp.2022.3187316"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2022.3187316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3187316","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5042363663","display_name":"Ying Hu","orcid":"https://orcid.org/0000-0001-7505-1767"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ying Hu","raw_affiliation_strings":["College of information science and engineering, Xinjiang University, Urumqi, China","college of information science and engineering, Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0001-7505-1767","affiliations":[{"raw_affiliation_string":"College of information science and engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"college of information science and engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061789480","display_name":"Yadong Chen","orcid":"https://orcid.org/0000-0002-6739-3123"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yadong Chen","raw_affiliation_strings":["College of information science and engineering, Xinjiang University, Urumqi, China","college of information science and engineering, Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0002-6739-3123","affiliations":[{"raw_affiliation_string":"College of information science and engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"college of information science and engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024585813","display_name":"Wenzhong Yang","orcid":"https://orcid.org/0000-0002-7017-129X"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhong Yang","raw_affiliation_strings":["College of information science and engineering, Xinjiang University, Urumqi, China","college of information science and engineering, Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0002-7017-129X","affiliations":[{"raw_affiliation_string":"College of information science and engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"college of information science and engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049944728","display_name":"Liang He","orcid":"https://orcid.org/0000-0003-4076-7479"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["Department of electrical engineering, Tsinghua University, Beijing, China","department of electrical engineering, Tsinghua University, Beijing, China","information science and engineering, Xinjiang University, China"],"raw_orcid":"https://orcid.org/0000-0003-4076-7479","affiliations":[{"raw_affiliation_string":"Department of electrical engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"department of electrical engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"information science and engineering, Xinjiang University, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024772368","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6604-0951"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["College of information science and engineering, Xinjiang University, Urumqi, China","college of information science and engineering, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of information science and engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"college of information science and engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042363663"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":3.8686,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.94396264,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"1517","last_page":"1521"},"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":0.9994000196456909,"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":0.9977999925613403,"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":0.8406406044960022},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7063578367233276},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6805137991905212},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.585466206073761},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.555756151676178},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5531734228134155},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5316738486289978},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.48834940791130066},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4732922911643982},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4731757938861847},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.46695905923843384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4572882056236267},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4532821774482727},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4361257255077362},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4089946448802948},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36252477765083313},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13198068737983704},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07886612415313721}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8406406044960022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7063578367233276},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6805137991905212},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.585466206073761},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.555756151676178},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5531734228134155},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5316738486289978},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.48834940791130066},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4732922911643982},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4731757938861847},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.46695905923843384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4572882056236267},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4532821774482727},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4361257255077362},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4089946448802948},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36252477765083313},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13198068737983704},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07886612415313721},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2022.3187316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3187316","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3931585407","display_name":null,"funder_award_id":"U1903213","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2752782242","https://openalex.org/W2796571515","https://openalex.org/W2894398294","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2963750251","https://openalex.org/W2963751183","https://openalex.org/W2963992487","https://openalex.org/W2966269666","https://openalex.org/W2970987838","https://openalex.org/W2972411915","https://openalex.org/W2973143779","https://openalex.org/W2990594533","https://openalex.org/W3015201698","https://openalex.org/W3015753416","https://openalex.org/W3034728336","https://openalex.org/W3034763882","https://openalex.org/W3037149862","https://openalex.org/W3081729342","https://openalex.org/W3099330747","https://openalex.org/W3111598519","https://openalex.org/W3133795225","https://openalex.org/W3160050861","https://openalex.org/W3162801840","https://openalex.org/W3170088519","https://openalex.org/W3184438937","https://openalex.org/W3197709460","https://openalex.org/W4298310324","https://openalex.org/W6631190155","https://openalex.org/W6751356808","https://openalex.org/W6751512325","https://openalex.org/W6766320909","https://openalex.org/W6774995033","https://openalex.org/W6777701575","https://openalex.org/W6783557883"],"related_works":["https://openalex.org/W3094316140","https://openalex.org/W3133205200","https://openalex.org/W4289363934","https://openalex.org/W2898145319","https://openalex.org/W2098101267","https://openalex.org/W2898606530","https://openalex.org/W4289362680","https://openalex.org/W2403380333","https://openalex.org/W2059119686","https://openalex.org/W2761596192"],"abstract_inverted_index":{"Recently,":[0],"the":[1,5,9,30,45,62,66,70,82,99,103,108,115,122,126,129,142,148,153,156,164,167,171],"time-domain-based":[2],"methods":[3,144],"(i.e.,":[4],"method":[6],"of":[7,69,117,155,160,166,180],"modeling":[8],"raw":[10],"waveform":[11],"directly)":[12],"for":[13,51,170],"audio":[14],"source":[15,175],"separation":[16],"have":[17],"shown":[18],"tremendous":[19],"potential.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24],"propose":[25],"a":[26,39,90,177],"model":[27,140],"which":[28],"combines":[29],"complexed":[31,73],"spectrogram":[32,74],"domain":[33,75],"feature":[34,37,91],"and":[35,43,72,101],"time-domain":[36,71],"by":[38],"cross-domain":[40],"encoder":[41],"(CDE)":[42],"adopts":[44],"hierarchic":[46],"temporal":[47],"convolutional":[48],"network":[49,63],"(HTCN)":[50],"multiple":[52],"music":[53],"sources":[54],"separation.":[55],"The":[56,111,132],"CDE":[57],"is":[58],"designed":[59,89,119],"to":[60,64,80,95],"enable":[61],"code":[65],"interactive":[67],"information":[68],"features.":[76],"HTCN":[77,100],"enables":[78],"it":[79],"learn":[81],"long-time":[83],"series":[84],"dependence":[85],"effectively.":[86],"We":[87,124],"also":[88],"calibration":[92],"unit":[93],"(FCU)":[94],"be":[96],"applied":[97],"in":[98,121],"adopted":[102],"multi-stage":[104],"training":[105,109],"strategy":[106],"during":[107],"stage.":[110],"ablation":[112],"study":[113],"demonstrates":[114],"effectiveness":[116],"each":[118],"component":[120],"model.":[123],"conducted":[125],"experiments":[127],"on":[128],"MUSDB18":[130],"dataset.":[131],"experimental":[133],"results":[134],"indicate":[135],"that":[136],"our":[137],"proposed":[138],"CDE-HTCN":[139],"outperforms":[141],"top-of-the-line":[143],"and,":[145],"compared":[146],"with":[147],"state-of-the-art":[149],"method,":[150],"DEMUCS,":[151],"achieves":[152],"improvement":[154,165],"average":[157],"SDR":[158,168],"score":[159,169],"0.61":[161],"dB.":[162,182],"Significantly,":[163],"<inline-formula><tex-math":[172],"notation=\"LaTeX\">$\\":[173],"bass$</tex-math></inline-formula>":[174],"has":[176],"sizable":[178],"margin":[179],"0.91":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}