{"id":"https://openalex.org/W3093725184","doi":"https://doi.org/10.1109/icassp39728.2021.9413896","title":"Lasaft: Latent Source Attentive Frequency Transformation For Conditioned Source Separation","display_name":"Lasaft: Latent Source Attentive Frequency Transformation For Conditioned Source Separation","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3093725184","doi":"https://doi.org/10.1109/icassp39728.2021.9413896","mag":"3093725184"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/2010.11631","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102881663","display_name":"Woosung Choi","orcid":"https://orcid.org/0000-0003-2638-2097"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Woosung Choi","raw_affiliation_strings":["Korea University","Korea University,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]},{"raw_affiliation_string":"Korea University,Department of Computer Science","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332534","display_name":"Minseok Kim","orcid":"https://orcid.org/0000-0003-4239-6245"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minseok Kim","raw_affiliation_strings":["Korea University","Korea University,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]},{"raw_affiliation_string":"Korea University,Department of Computer Science","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000577702","display_name":"Jaehwa Chung","orcid":"https://orcid.org/0000-0002-1904-7189"},"institutions":[{"id":"https://openalex.org/I124125349","display_name":"Korea National Open University","ror":"https://ror.org/016ebag96","country_code":"KR","type":"education","lineage":["https://openalex.org/I124125349"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaehwa Chung","raw_affiliation_strings":["Korea National Open University","Korea National Open University,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea National Open University","institution_ids":["https://openalex.org/I124125349"]},{"raw_affiliation_string":"Korea National Open University,Department of Computer Science","institution_ids":["https://openalex.org/I124125349"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043500102","display_name":"Soonyoung Jung","orcid":"https://orcid.org/0000-0003-2693-9377"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soonyoung Jung","raw_affiliation_strings":["Korea University","Korea University,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]},{"raw_affiliation_string":"Korea University,Department of Computer Science","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4633,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58552588,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"171","last_page":"175"},"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":0.9969000220298767,"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":0.9966999888420105,"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/source-separation","display_name":"Source separation","score":0.7574973702430725},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.6942883133888245},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6765056848526001},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5479337573051453},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.5222305059432983},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4952801764011383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4634876549243927},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.45596641302108765},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41690096259117126},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4139212965965271},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32466936111450195},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14563268423080444},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11760607361793518},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08347290754318237}],"concepts":[{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7574973702430725},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.6942883133888245},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6765056848526001},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5479337573051453},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.5222305059432983},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4952801764011383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4634876549243927},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.45596641302108765},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41690096259117126},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4139212965965271},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32466936111450195},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14563268423080444},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11760607361793518},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08347290754318237},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.11631","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.11631","pdf_url":"https://arxiv.org/pdf/2010.11631","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":null,"raw_type":"text"},{"id":"mag:3093725184","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.11631v2","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":"doi:10.48550/arxiv.2010.11631","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.11631","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"},{"id":"doi:10.17023/064m-7t96","is_oa":true,"landing_page_url":"https://doi.org/10.17023/064m-7t96","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"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:2010.11631","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.11631","pdf_url":"https://arxiv.org/pdf/2010.11631","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3093725184.pdf"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W1901129140","https://openalex.org/W2127851351","https://openalex.org/W2156387975","https://openalex.org/W2669032454","https://openalex.org/W2760103357","https://openalex.org/W2774707525","https://openalex.org/W2954304925","https://openalex.org/W2963403868","https://openalex.org/W2963446712","https://openalex.org/W2963751183","https://openalex.org/W2963921132","https://openalex.org/W2964070952","https://openalex.org/W2964121744","https://openalex.org/W2964607787","https://openalex.org/W2985607490","https://openalex.org/W2991107219","https://openalex.org/W3015753416","https://openalex.org/W3035268204","https://openalex.org/W3090496396","https://openalex.org/W3122111104","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6639824700","https://openalex.org/W6682889407","https://openalex.org/W6725739302","https://openalex.org/W6739901393","https://openalex.org/W6746914816","https://openalex.org/W6766320909","https://openalex.org/W6770282137","https://openalex.org/W6774995033","https://openalex.org/W6783557883","https://openalex.org/W6784335252"],"related_works":["https://openalex.org/W3162801840","https://openalex.org/W2952537815","https://openalex.org/W5438320","https://openalex.org/W2922067843","https://openalex.org/W3115253782","https://openalex.org/W3152666233","https://openalex.org/W2075448601","https://openalex.org/W3090933449","https://openalex.org/W2767126465","https://openalex.org/W3130471138","https://openalex.org/W3161447515","https://openalex.org/W2107730617","https://openalex.org/W1826959296","https://openalex.org/W1999092158","https://openalex.org/W2230934893","https://openalex.org/W2964701588","https://openalex.org/W2624825481","https://openalex.org/W3131701899","https://openalex.org/W3136671356","https://openalex.org/W3082965233"],"abstract_inverted_index":{"Recent":[0],"deep-learning":[1],"approaches":[2],"have":[3],"shown":[4],"that":[5,91],"Frequency":[6,43],"Transformation":[7,44],"(FT)":[8],"blocks":[9],"can":[10,96],"significantly":[11],"improve":[12,97],"spectrogram-based":[13],"single-source":[14],"separation":[15,109],"models":[16],"by":[17],"capturing":[18],"frequency":[19,50],"patterns.":[20,51],"The":[21],"goal":[22],"of":[23,63],"this":[24],"paper":[25],"is":[26],"to":[27,32,47,68],"extend":[28,79],"the":[29,34,39,55,80,87,98],"FT":[30],"block":[31,46],"fit":[33],"multi-source":[35,84],"task.":[36],"We":[37,52],"propose":[38,54],"Latent":[40],"Source":[41],"Attentive":[42],"(LaSAFT)":[45],"capture":[48],"source-dependent":[49],"also":[53],"Gated":[56],"Point-wise":[57],"Convolutional":[58],"Modulation":[59,66],"(GPoCM),":[60],"an":[61],"extension":[62],"Feature-wise":[64],"Linear":[65],"(FiLM),":[67],"modulate":[69],"internal":[70],"features.":[71],"By":[72],"employing":[73],"these":[74],"two":[75],"novel":[76],"methods,":[77],"we":[78],"Conditioned-U-Net":[81],"(CUNet)":[82],"for":[83],"separation,":[85],"and":[86,94],"experimental":[88],"results":[89],"indicate":[90],"our":[92],"LaSAFT":[93],"GPoCM":[95],"CUNet\u2019s":[99],"performance,":[100],"achieving":[101],"state-of-the-art":[102],"SDR":[103],"performance":[104],"on":[105],"several":[106],"MUSDB18":[107],"source":[108],"tasks.":[110]},"counts_by_year":[{"year":2021,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}