{"id":"https://openalex.org/W2943228221","doi":"https://doi.org/10.1109/waspaa.2019.8937079","title":"Investigating Kernel Shapes and Skip Connections for Deep Learning-Based Harmonic-Percussive Separation","display_name":"Investigating Kernel Shapes and Skip Connections for Deep Learning-Based Harmonic-Percussive Separation","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2943228221","doi":"https://doi.org/10.1109/waspaa.2019.8937079","mag":"2943228221"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2019.8937079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2019.8937079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.01899","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059785530","display_name":"Carlos Lordelo","orcid":"https://orcid.org/0000-0002-7906-4677"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Carlos Lordelo","raw_affiliation_strings":["Centre for Digital Music, Queen Mary University of London, London, UK","Queen Mary University of London Centre for Digital Music London UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Queen Mary University of London Centre for Digital Music London UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084672392","display_name":"Emmanouil Benetos","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emmanouil Benetos","raw_affiliation_strings":["Centre for Digital Music, Queen Mary University of London, London, UK","Queen Mary University of London Centre for Digital Music London UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Queen Mary University of London Centre for Digital Music London UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077484271","display_name":"Simon Dixon","orcid":"https://orcid.org/0000-0002-6098-481X"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon Dixon","raw_affiliation_strings":["Centre for Digital Music, Queen Mary University of London, London, UK","Queen Mary University of London Centre for Digital Music London UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Queen Mary University of London Centre for Digital Music London UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073161410","display_name":"Sven Ahlb\u00e4ck","orcid":"https://orcid.org/0000-0002-4756-1441"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sven Ahlback","raw_affiliation_strings":["Doremir Music Research AB, Stockholm, Sweden","Doremir Music Research AB,Stockholm,Sweden"],"affiliations":[{"raw_affiliation_string":"Doremir Music Research AB, Stockholm, Sweden","institution_ids":[]},{"raw_affiliation_string":"Doremir Music Research AB,Stockholm,Sweden","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059785530"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03266577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"40","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T11447","display_name":"Blind Source Separation Techniques","score":0.9922000169754028,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7253198623657227},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7057380676269531},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.681140661239624},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.6277834177017212},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5987006425857544},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5640337467193604},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.48620811104774475},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4678806662559509},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4158977270126343},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3746510446071625},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33730971813201904},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12560516595840454},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10813549160957336}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7253198623657227},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7057380676269531},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.681140661239624},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.6277834177017212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5987006425857544},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5640337467193604},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.48620811104774475},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4678806662559509},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4158977270126343},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3746510446071625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33730971813201904},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12560516595840454},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10813549160957336},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/waspaa.2019.8937079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2019.8937079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.01899","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.01899","pdf_url":"https://arxiv.org/pdf/1905.01899","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2943228221","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1905.01899.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/59067","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/59067","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},{"id":"doi:10.48550/arxiv.1905.01899","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.01899","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.01899","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.01899","pdf_url":"https://arxiv.org/pdf/1905.01899","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2943228221.pdf","grobid_xml":"https://content.openalex.org/works/W2943228221.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1561135842","https://openalex.org/W1901129140","https://openalex.org/W1979932443","https://openalex.org/W2062710265","https://openalex.org/W2126264921","https://openalex.org/W2197991991","https://openalex.org/W2502139158","https://openalex.org/W2583165630","https://openalex.org/W2604509013","https://openalex.org/W2669032454","https://openalex.org/W2765931784","https://openalex.org/W2771132365","https://openalex.org/W2774707525","https://openalex.org/W2884537779","https://openalex.org/W2963141945","https://openalex.org/W2963158330","https://openalex.org/W2963446712","https://openalex.org/W2963452667","https://openalex.org/W2963750251","https://openalex.org/W2963992487","https://openalex.org/W6633727632","https://openalex.org/W6639824700","https://openalex.org/W6657159850","https://openalex.org/W6744013906","https://openalex.org/W6746914816","https://openalex.org/W6751512325","https://openalex.org/W6766320909"],"related_works":["https://openalex.org/W2967200242","https://openalex.org/W2953173407","https://openalex.org/W3121912046","https://openalex.org/W2898848345","https://openalex.org/W3012435458","https://openalex.org/W2990215755","https://openalex.org/W2963939958","https://openalex.org/W3013431865","https://openalex.org/W3091736716","https://openalex.org/W3198041036","https://openalex.org/W2899187156","https://openalex.org/W3182611303","https://openalex.org/W3109101583","https://openalex.org/W2981609494","https://openalex.org/W3091445043","https://openalex.org/W3035718760","https://openalex.org/W1527646298","https://openalex.org/W2996328914","https://openalex.org/W2905272567","https://openalex.org/W2771111398"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,21],"propose":[4],"an":[5],"efficient":[6],"deep":[7,108],"learning":[8,112],"encoder-decoder":[9],"network":[10,68,109],"for":[11,54],"performing":[12],"Harmonic-Percussive":[13],"Source":[14],"Separation":[15],"(HPSS).":[16],"It":[17],"is":[18],"shown":[19],"that":[20,105],"are":[22],"able":[23],"to":[24,69],"greatly":[25],"reduce":[26],"the":[27,42,48,55,59,63,67,71,88,94,100,106,126],"number":[28,127],"of":[29,38,50,58,65,87,99,113,128],"model":[30,43],"trainable":[31],"parameters":[32,129],"by":[33],"using":[34,93],"a":[35,121],"dense":[36],"arrangement":[37],"skip":[39],"connections":[40],"between":[41],"layers.":[44],"We":[45],"also":[46],"explore":[47],"utilisation":[49],"different":[51,72],"kernel":[52],"sizes":[53],"2D":[56],"filters":[57],"convolutional":[60],"layers":[61],"with":[62,76],"objective":[64],"allowing":[66],"learn":[70],"time-frequency":[73],"patterns":[74],"associated":[75],"percussive":[77],"and":[78,85,96,116,130],"harmonic":[79],"sources":[80],"more":[81],"efficiently.":[82],"The":[83],"training":[84,95,131],"evaluation":[86],"separation":[89],"has":[90],"been":[91],"done":[92],"test":[97],"sets":[98],"MUSDB18":[101],"dataset.":[102],"Results":[103],"show":[104],"proposed":[107],"achieves":[110],"automatic":[111],"high-level":[114],"features":[115],"maintains":[117],"HPSS":[118],"performance":[119],"at":[120],"state-of-the-art":[122],"level":[123],"while":[124],"reducing":[125],"time.":[132]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}