{"id":"https://openalex.org/W4293518551","doi":"https://doi.org/10.1109/icme52920.2022.9859957","title":"Multi-Scale Temporal-Frequency Attention for Music Source Separation","display_name":"Multi-Scale Temporal-Frequency Attention for Music Source Separation","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293518551","doi":"https://doi.org/10.1109/icme52920.2022.9859957"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859957","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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/A5072495935","display_name":"Lianwu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]},{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lianwu Chen","raw_affiliation_strings":["Kuaishou Technology Co.,Beijing,China","Kuaishou Technology Co., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co.,Beijing,China","institution_ids":["https://openalex.org/I4210155967"]},{"raw_affiliation_string":"Kuaishou Technology Co., Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034844592","display_name":"Xiguang Zheng","orcid":"https://orcid.org/0000-0003-3103-9090"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]},{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiguang Zheng","raw_affiliation_strings":["Kuaishou Technology Co.,Beijing,China","Kuaishou Technology Co., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co.,Beijing,China","institution_ids":["https://openalex.org/I4210155967"]},{"raw_affiliation_string":"Kuaishou Technology Co., Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374052","display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0001-5773-9090"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]},{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Zhang","raw_affiliation_strings":["Kuaishou Technology Co.,Beijing,China","Kuaishou Technology Co., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co.,Beijing,China","institution_ids":["https://openalex.org/I4210155967"]},{"raw_affiliation_string":"Kuaishou Technology Co., Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614099","display_name":"Liang Guo","orcid":"https://orcid.org/0000-0001-7759-5784"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]},{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Guo","raw_affiliation_strings":["Kuaishou Technology Co.,Beijing,China","Kuaishou Technology Co., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co.,Beijing,China","institution_ids":["https://openalex.org/I4210155967"]},{"raw_affiliation_string":"Kuaishou Technology Co., Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009065607","display_name":"Bing Yu","orcid":"https://orcid.org/0009-0004-7297-9307"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]},{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Yu","raw_affiliation_strings":["Kuaishou Technology Co.,Beijing,China","Kuaishou Technology Co., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co.,Beijing,China","institution_ids":["https://openalex.org/I4210155967"]},{"raw_affiliation_string":"Kuaishou Technology Co., Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5072495935"],"corresponding_institution_ids":["https://openalex.org/I4210155967","https://openalex.org/I4401726859"],"apc_list":null,"apc_paid":null,"fwci":0.6137,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65308057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"401","issue":null,"first_page":"1","last_page":"6"},"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":0.9997000098228455,"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":0.9979000091552734,"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":0.9327974319458008},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7264714241027832},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7058402299880981},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6132138967514038},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.5417845845222473},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5365778207778931},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5338809490203857},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4683249294757843},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.46675992012023926},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4656186103820801},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4413908123970032},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12135067582130432},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06948208808898926}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9327974319458008},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7264714241027832},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7058402299880981},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6132138967514038},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.5417845845222473},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5365778207778931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5338809490203857},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4683249294757843},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.46675992012023926},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4656186103820801},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4413908123970032},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12135067582130432},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06948208808898926},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9859957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859957","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1594771616","https://openalex.org/W1902027874","https://openalex.org/W2018735295","https://openalex.org/W2022668263","https://openalex.org/W2058676219","https://openalex.org/W2097361095","https://openalex.org/W2127851351","https://openalex.org/W2399467590","https://openalex.org/W2563534197","https://openalex.org/W2669032454","https://openalex.org/W2774707525","https://openalex.org/W2917831833","https://openalex.org/W2938709889","https://openalex.org/W2963452667","https://openalex.org/W2963750251","https://openalex.org/W2963751183","https://openalex.org/W2964607787","https://openalex.org/W2972411915","https://openalex.org/W2990594533","https://openalex.org/W3012897083","https://openalex.org/W3037149862","https://openalex.org/W3090496396","https://openalex.org/W3092379909","https://openalex.org/W3094893721","https://openalex.org/W3113290170","https://openalex.org/W3133795225","https://openalex.org/W3199957557","https://openalex.org/W3213726885","https://openalex.org/W4226300471","https://openalex.org/W4286980120","https://openalex.org/W4385245566","https://openalex.org/W6712494307","https://openalex.org/W6746914816","https://openalex.org/W6751512325","https://openalex.org/W6775369996","https://openalex.org/W6783557883","https://openalex.org/W6784335252","https://openalex.org/W6787607767","https://openalex.org/W6801426729"],"related_works":["https://openalex.org/W4253838456","https://openalex.org/W3089904752","https://openalex.org/W2029956926","https://openalex.org/W1978977443","https://openalex.org/W2152457943","https://openalex.org/W2040266362","https://openalex.org/W2997975677","https://openalex.org/W2371459421","https://openalex.org/W2059119686","https://openalex.org/W1941000114"],"abstract_inverted_index":{"In":[0,53],"recent":[1],"years,":[2],"deep":[3],"neural":[4],"networks":[5],"(DNNs)":[6],"based":[7],"approaches":[8],"have":[9,22,44],"achieved":[10],"the":[11,24,32,38,50,64,82,95,99,111,116],"start-of-the-art":[12],"performance":[13],"for":[14,49,84],"music":[15,39,85],"source":[16],"separation":[17],"(MSS).":[18],"Although":[19],"previous":[20],"methods":[21],"addressed":[23],"large":[25],"receptive":[26],"field":[27],"modeling":[28],"using":[29],"various":[30],"methods,":[31],"temporal":[33,69],"and":[34,70],"frequency":[35,71],"correlations":[36,66,83],"of":[37,120],"spectrogram":[40,65],"with":[41,103],"repeated":[42],"patterns":[43],"not":[45],"been":[46],"explicitly":[47],"explored":[48],"MSS":[51],"task.":[52],"this":[54],"paper,":[55],"a":[56,74],"temporal-frequency":[57],"attention":[58,76],"module":[59],"is":[60,77,115],"proposed":[61,78,96],"to":[62,79],"model":[63],"along":[67],"both":[68],"dimensions.":[72],"Moreover,":[73],"multi-scale":[75],"effectively":[80],"capture":[81],"signal.":[86],"The":[87],"experimental":[88],"results":[89],"on":[90,109],"MUSDB18":[91],"dataset":[92],"show":[93],"that":[94],"method":[97],"outperforms":[98],"existing":[100],"state-of-the-art":[101],"systems":[102],"9.51":[104],"dB":[105],"signal-to-distortion":[106],"ratio":[107],"(SDR)":[108],"separating":[110],"vocal":[112],"stems,":[113],"which":[114],"primary":[117],"practical":[118],"application":[119],"MSS.":[121]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}