{"id":"https://openalex.org/W4391021794","doi":"https://doi.org/10.1109/asru57964.2023.10389670","title":"MBTFNET: Multi-Band Temporal-Frequency Neural Network for Singing Voice Enhancement","display_name":"MBTFNET: Multi-Band Temporal-Frequency Neural Network for Singing Voice Enhancement","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021794","doi":"https://doi.org/10.1109/asru57964.2023.10389670"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5120218349","display_name":"Weiming Xu","orcid":"https://orcid.org/0000-0002-3008-8539"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiming Xu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044361794","display_name":"Zhouxuan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhouxuan Chen","raw_affiliation_strings":["Lyra Lab, Tencent Music Entertainment,Shenzhen,China","Lyra Lab, Tencent Music Entertainment, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lyra Lab, Tencent Music Entertainment,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Lyra Lab, Tencent Music Entertainment, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036359785","display_name":"Zhili Tan","orcid":"https://orcid.org/0000-0002-2445-5240"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhili Tan","raw_affiliation_strings":["Lyra Lab, Tencent Music Entertainment,Shenzhen,China","Lyra Lab, Tencent Music Entertainment, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lyra Lab, Tencent Music Entertainment,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Lyra Lab, Tencent Music Entertainment, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017208328","display_name":"Shubo Lv","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shubo Lv","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091225905","display_name":"Runduo Han","orcid":"https://orcid.org/0009-0009-4380-4424"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runduo Han","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100583054","display_name":"Wenjiang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjiang Zhou","raw_affiliation_strings":["Lyra Lab, Tencent Music Entertainment,Shenzhen,China","Lyra Lab, Tencent Music Entertainment, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lyra Lab, Tencent Music Entertainment,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Lyra Lab, Tencent Music Entertainment, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101481948","display_name":"Weifeng Zhao","orcid":"https://orcid.org/0009-0007-0533-0120"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng Zhao","raw_affiliation_strings":["Lyra Lab, Tencent Music Entertainment,Shenzhen,China","Lyra Lab, Tencent Music Entertainment, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lyra Lab, Tencent Music Entertainment,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Lyra Lab, Tencent Music Entertainment, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3695,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58833725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9948999881744385,"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/singing","display_name":"Singing","score":0.8789854645729065},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.702417254447937},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6957889795303345},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6891145706176758},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49537360668182373},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49372610449790955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3423284590244293},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3343678116798401},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20746833086013794},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07343578338623047}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8789854645729065},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.702417254447937},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6957889795303345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6891145706176758},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49537360668182373},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49372610449790955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3423284590244293},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3343678116798401},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20746833086013794},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07343578338623047},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1481646516","https://openalex.org/W1901129140","https://openalex.org/W2291877678","https://openalex.org/W2937525188","https://openalex.org/W2964058413","https://openalex.org/W2972411915","https://openalex.org/W2973062255","https://openalex.org/W2990594533","https://openalex.org/W3015199127","https://openalex.org/W3024869864","https://openalex.org/W3096408984","https://openalex.org/W3097653961","https://openalex.org/W3097906045","https://openalex.org/W3133795225","https://openalex.org/W3162493033","https://openalex.org/W3197042120","https://openalex.org/W3198543387","https://openalex.org/W3198680319","https://openalex.org/W3211438798","https://openalex.org/W4221150474","https://openalex.org/W4221151515","https://openalex.org/W4224917453","https://openalex.org/W4224919629","https://openalex.org/W4224932531","https://openalex.org/W4225298533","https://openalex.org/W4225905067","https://openalex.org/W4226221107","https://openalex.org/W4298310324","https://openalex.org/W4375928773","https://openalex.org/W6628727242","https://openalex.org/W6757632829","https://openalex.org/W6766320909","https://openalex.org/W6801426729","https://openalex.org/W6810984764"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853"],"abstract_inverted_index":{"A":[0],"typical":[1],"neural":[2,71],"speech":[3,9],"enhancement":[4,20,135],"(SE)":[5],"approach":[6],"mainly":[7],"handles":[8],"and":[10,30,44,84,94,108,111,162],"noise":[11,83],"mixtures,":[12],"which":[13,49,78,144],"is":[14,24],"not":[15],"optimal":[16],"for":[17,74,97,126],"singing":[18,23,31,75,89],"voice":[19,76],"scenarios":[21],"where":[22],"often":[25],"mixed":[26],"with":[27],"vocal-correlated":[28],"accompanies":[29],"has":[32],"substantial":[33],"differences":[34],"from":[35,88],"speaking.":[36],"Music":[37],"source":[38],"separation":[39],"(MSS)":[40],"models":[41],"treat":[42],"vocals":[43,87],"various":[45],"accompaniment":[46],"components":[47],"equally,":[48],"may":[50],"reduce":[51],"performance":[52,148],"compared":[53],"to":[54,117],"the":[55,106,119,123,147],"model":[56,156],"that":[57,153],"only":[58],"considers":[59],"vocal":[60],"enhancement.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65,130],"propose":[66,131],"a":[67],"novel":[68],"multi-band":[69],"temporal-frequency":[70],"network":[72],"(MBTFNet)":[73],"enhancement,":[77],"particularly":[79],"removes":[80],"background":[81],"music,":[82],"even":[85],"backing":[86,128],"recordings.":[90],"MBTFNet":[91],"combines":[92],"inter":[93],"intra-band":[95],"modeling":[96,104],"better":[98],"processing":[99],"of":[100,122,149],"full-band":[101],"signals.":[102],"Dual-path":[103],"in":[105],"temporal":[107,112],"frequency":[109],"axis":[110],"dilation":[113],"blocks":[114],"are":[115],"introduced":[116],"expand":[118],"receptive":[120],"field":[121],"model.":[124],"Particularly":[125],"removing":[127],"vocals,":[129],"an":[132],"implicit":[133],"personalized":[134],"(IPE)":[136],"stage":[137],"based":[138],"on":[139],"signal-to-noise":[140],"ratio":[141],"(SNR)":[142],"estimation,":[143],"further":[145],"improves":[146],"MBTFNet.":[150],"Experiments":[151],"show":[152],"our":[154],"proposed":[155],"significantly":[157],"outperforms":[158],"several":[159],"state-of-the-art":[160],"SE":[161],"MSS":[163],"models.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}