{"id":"https://openalex.org/W3000675699","doi":"https://doi.org/10.1109/ism46123.2019.00034","title":"OveNet: A Hyper-Range U-Net for Singing Voice Separation","display_name":"OveNet: A Hyper-Range U-Net for Singing Voice Separation","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3000675699","doi":"https://doi.org/10.1109/ism46123.2019.00034","mag":"3000675699"},"language":"en","primary_location":{"id":"doi:10.1109/ism46123.2019.00034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ism46123.2019.00034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Multimedia (ISM)","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/A5084633367","display_name":"Chi-Sheng Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chi-Sheng Wu","raw_affiliation_strings":["National Tsing Hua University","Institute of Information Systems and Applications National Tsing Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Institute of Information Systems and Applications National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033349098","display_name":"Shiang Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shiang Lee","raw_affiliation_strings":["National Tsing Hua University","Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080558475","display_name":"Von\u2010Wun Soo","orcid":"https://orcid.org/0000-0002-4810-1244"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Von-Wun Soo","raw_affiliation_strings":["National Tsing Hua University","Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084633367"],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17086044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"148","last_page":"1483"},"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.9077426791191101},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7895816564559937},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7385064363479614},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6944368481636047},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.678369402885437},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5928852558135986},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5775076746940613},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5173704028129578},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.5139879584312439},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.46680760383605957},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4590541124343872},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4451099932193756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4133756160736084},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.26423007249832153},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2314971387386322},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.16088691353797913},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12966325879096985},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10174524784088135},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09411594271659851}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9077426791191101},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7895816564559937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7385064363479614},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6944368481636047},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.678369402885437},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5928852558135986},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5775076746940613},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5173704028129578},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.5139879584312439},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.46680760383605957},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4590541124343872},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4451099932193756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4133756160736084},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.26423007249832153},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2314971387386322},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.16088691353797913},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12966325879096985},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10174524784088135},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09411594271659851},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ism46123.2019.00034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ism46123.2019.00034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Multimedia (ISM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2097117768","https://openalex.org/W2127851351","https://openalex.org/W2774707525","https://openalex.org/W2921904817","https://openalex.org/W2963751183","https://openalex.org/W2963992487","https://openalex.org/W2964070952","https://openalex.org/W4298310324","https://openalex.org/W6639824700"],"related_works":["https://openalex.org/W3094316140","https://openalex.org/W3133205200","https://openalex.org/W2898145319","https://openalex.org/W4289363934","https://openalex.org/W2098101267","https://openalex.org/W1509813908","https://openalex.org/W2059119686","https://openalex.org/W2898606530","https://openalex.org/W4289362680","https://openalex.org/W2403380333"],"abstract_inverted_index":{"In":[0],"the":[1,46],"audio":[2,48,51],"source":[3],"separation":[4],"topic,":[5],"most":[6],"researchers":[7],"based":[8],"on":[9,69],"deep":[10],"learning":[11],"methods":[12],"ignored":[13],"higher-frequency":[14],"signals":[15,49],"due":[16],"to":[17,44],"lack":[18],"of":[19],"efficient":[20],"data":[21,74],"compression":[22],"method.":[23],"We":[24],"propose":[25],"a":[26],"new":[27],"model":[28],"named":[29],"OvertoneNet":[30],"(OveNet)":[31],"that":[32,59],"adopts":[33],"two":[34],"novel":[35],"concepts,":[36],"frequency":[37],"1x1":[38],"convolution":[39],"layers,":[40],"and":[41,66],"complex-spectrogram":[42],"channels,":[43],"handle":[45],"44.1k":[47],"(Hi-Res":[50],"signals)":[52],"containing":[53],"full":[54],"overtones.":[55],"The":[56],"result":[57],"shows":[58],"OveNet":[60],"performs":[61],"well":[62],"in":[63],"both":[64],"objective":[65],"subjective":[67],"evaluation":[68],"interference":[70],"using":[71],"limited":[72],"training":[73],"from":[75],"SiSEC2018.":[76]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}