{"id":"https://openalex.org/W3015611910","doi":"https://doi.org/10.1109/icassp40776.2020.9053542","title":"Towards Real-Time Single-Channel Singing-Voice Separation with Pruned Multi-Scaled Densenets","display_name":"Towards Real-Time Single-Channel Singing-Voice Separation with Pruned Multi-Scaled Densenets","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015611910","doi":"https://doi.org/10.1109/icassp40776.2020.9053542","mag":"3015611910"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053542","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053542","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/A5032121938","display_name":"Markus Huber","orcid":null},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["AT","US"],"is_corresponding":true,"raw_author_name":"Markus Huber","raw_affiliation_strings":["Signal Processing and Speech Communication Lab, Graz University of Technology"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Lab, Graz University of Technology","institution_ids":["https://openalex.org/I4092182","https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073596132","display_name":"G\u00fcnther Schindler","orcid":null},"institutions":[{"id":"https://openalex.org/I85384741","display_name":"Heidelberg University","ror":"https://ror.org/04rcqnp59","country_code":"US","type":"education","lineage":["https://openalex.org/I85384741"]},{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Gunther Schindler","raw_affiliation_strings":["Institute of Computer Engineering, Heidelberg University"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Engineering, Heidelberg University","institution_ids":["https://openalex.org/I85384741","https://openalex.org/I223822909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028009433","display_name":"Christian Schorkhuber","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christian Schorkhuber","raw_affiliation_strings":["sonible GmbH"],"affiliations":[{"raw_affiliation_string":"sonible GmbH","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019416885","display_name":"Wolfgang Roth","orcid":"https://orcid.org/0000-0002-0778-2418"},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]},{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT","US"],"is_corresponding":false,"raw_author_name":"Wolfgang Roth","raw_affiliation_strings":["Signal Processing and Speech Communication Lab, Graz University of Technology"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Lab, Graz University of Technology","institution_ids":["https://openalex.org/I4092182","https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015798259","display_name":"Franz Pernkopf","orcid":"https://orcid.org/0000-0002-6356-3367"},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]},{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT","US"],"is_corresponding":false,"raw_author_name":"Franz Pernkopf","raw_affiliation_strings":["Signal Processing and Speech Communication Lab, Graz University of Technology"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Lab, Graz University of Technology","institution_ids":["https://openalex.org/I4092182","https://openalex.org/I4210121626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014251134","display_name":"Holger Fr\u00f6ning","orcid":"https://orcid.org/0000-0001-9562-0680"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]},{"id":"https://openalex.org/I85384741","display_name":"Heidelberg University","ror":"https://ror.org/04rcqnp59","country_code":"US","type":"education","lineage":["https://openalex.org/I85384741"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Holger Froning","raw_affiliation_strings":["Institute of Computer Engineering, Heidelberg University"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Engineering, Heidelberg University","institution_ids":["https://openalex.org/I85384741","https://openalex.org/I223822909"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5032121938"],"corresponding_institution_ids":["https://openalex.org/I4092182","https://openalex.org/I4210121626"],"apc_list":null,"apc_paid":null,"fwci":0.6061,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65148124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"806","last_page":"810"},"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":0.9998999834060669,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/bottleneck","display_name":"Bottleneck","score":0.8489540815353394},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7993029356002808},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6129186749458313},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5804914236068726},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5293287038803101},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5211400985717773},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5088825225830078},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5053449273109436},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.45574143528938293},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4326937198638916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3404563069343567},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3292514681816101},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2379676103591919},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21739396452903748},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.09399807453155518}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8489540815353394},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993029356002808},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6129186749458313},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5804914236068726},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5293287038803101},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5211400985717773},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5088825225830078},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5053449273109436},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.45574143528938293},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4326937198638916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3404563069343567},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3292514681816101},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2379676103591919},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21739396452903748},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.09399807453155518},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053542","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053542","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":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1529883046","https://openalex.org/W2221409856","https://openalex.org/W2552071709","https://openalex.org/W2601999498","https://openalex.org/W2737788279","https://openalex.org/W2768282280","https://openalex.org/W2774707525","https://openalex.org/W2783000019","https://openalex.org/W2883780447","https://openalex.org/W2884537779","https://openalex.org/W2886067286","https://openalex.org/W2891405874","https://openalex.org/W2899748887","https://openalex.org/W2938483616","https://openalex.org/W2949804919","https://openalex.org/W2950577002","https://openalex.org/W2963342610","https://openalex.org/W2963446712","https://openalex.org/W2963452667","https://openalex.org/W2963698842","https://openalex.org/W2963750251","https://openalex.org/W2963751183","https://openalex.org/W2963992487","https://openalex.org/W2972411915","https://openalex.org/W3128292107","https://openalex.org/W4298310324","https://openalex.org/W4300092737","https://openalex.org/W4311415687","https://openalex.org/W6688843265","https://openalex.org/W6725739302","https://openalex.org/W6729728456","https://openalex.org/W6735444749","https://openalex.org/W6741267457","https://openalex.org/W6746052068","https://openalex.org/W6746914816","https://openalex.org/W6749810415","https://openalex.org/W6751356808","https://openalex.org/W6751512325","https://openalex.org/W6753767121","https://openalex.org/W6753918066","https://openalex.org/W6761368507","https://openalex.org/W6764558160","https://openalex.org/W6766320909","https://openalex.org/W6772849459"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W1494268238","https://openalex.org/W2077498359"],"abstract_inverted_index":{"Modern":[0],"musical":[1],"source":[2,53],"separation":[3,14,54,110,134],"systems":[4],"based":[5],"on":[6,108],"deep":[7,82],"neural":[8],"networks":[9],"reach":[10],"unprecedented":[11],"levels":[12],"of":[13,20,74,101,126],"quality.":[15],"However,":[16],"harnessing":[17],"the":[18,44,59,68,93,109,115,120,133],"power":[19],"these":[21],"large-scale":[22],"models":[23],"in":[24,47],"typical":[25],"audio":[26],"production":[27],"environments,":[28],"which":[29],"frequently":[30],"offer":[31],"only":[32],"limited":[33],"computing":[34],"resources":[35],"while":[36,77,131],"demanding":[37],"real-time":[38,52],"processing,":[39],"remains":[40],"challenging.":[41],"We":[42,112],"extend":[43],"multi-scaled":[45],"DenseNet":[46],"several":[48],"aspects":[49],"to":[50,90],"facilitate":[51],"scenarios.":[55],"Specifically,":[56],"we":[57,87],"reduce":[58,114],"computational":[60,121],"requirements":[61],"by":[62,96,123],"inferring":[63],"Mel-scaled":[64],"masks":[65],"and":[66,118,128],"decrease":[67],"model":[69,94,116],"size":[70,117],"via":[71],"effective":[72],"use":[73],"bottleneck":[75],"layers,":[76],"improving":[78],"performance":[79],"using":[80],"a":[81,124],"clustering":[83],"objective.":[84],"In":[85],"addition,":[86],"are":[88],"able":[89],"further":[91],"increase":[92,119],"efficiency":[95,122],"applying":[97],"parameterized":[98],"structured":[99],"pruning":[100],"convolutional":[102],"weights":[103],"without":[104],"any":[105],"significant":[106],"impact":[107],"performance.":[111,135],"significantly":[113],"factor":[125],"1.6":[127],"4.3,":[129],"respectively,":[130],"maintaining":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}