{"id":"https://openalex.org/W4392903017","doi":"https://doi.org/10.1109/icassp48485.2024.10446287","title":"Stereophonic Music Source Separation with Spatially-Informed Bridging Band-Split Network","display_name":"Stereophonic Music Source Separation with Spatially-Informed Bridging Band-Split Network","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903017","doi":"https://doi.org/10.1109/icassp48485.2024.10446287"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5106698171","display_name":"Yichen Yang","orcid":"https://orcid.org/0009-0007-4812-1900"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]},{"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","JP"],"is_corresponding":true,"raw_author_name":"Yichen Yang","raw_affiliation_strings":["Northwestern Polytechnical University,Center of Intelligent Acoustics and Immersive Communications,Xi&#x2019;an,China","Graduate School of Information, Production and Systems, Waseda University, Kitakyushu, Japan"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Center of Intelligent Acoustics and Immersive Communications,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Graduate School of Information, Production and Systems, Waseda University, Kitakyushu, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028125561","display_name":"Haowen Li","orcid":"https://orcid.org/0000-0003-2746-4000"},"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":"Haowen Li","raw_affiliation_strings":["Northwestern Polytechnical University,Center of Intelligent Acoustics and Immersive Communications,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Center of Intelligent Acoustics and Immersive Communications,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044246151","display_name":"Xianrui Wang","orcid":"https://orcid.org/0000-0002-8715-4111"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]},{"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","JP"],"is_corresponding":false,"raw_author_name":"Xianrui Wang","raw_affiliation_strings":["Northwestern Polytechnical University,Center of Intelligent Acoustics and Immersive Communications,Xi&#x2019;an,China","Graduate School of Information, Production and Systems, Waseda University, Kitakyushu, Japan"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Center of Intelligent Acoustics and Immersive Communications,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Graduate School of Information, Production and Systems, Waseda University, Kitakyushu, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059258204","display_name":"Wen Zhang","orcid":"https://orcid.org/0000-0002-0752-6123"},"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":"Wen Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,Center of Intelligent Acoustics and Immersive Communications,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Center of Intelligent Acoustics and Immersive Communications,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075702573","display_name":"Shoji Makino","orcid":"https://orcid.org/0000-0003-1934-640X"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoji Makino","raw_affiliation_strings":["Waseda University,Graduate School of Information, Production and Systems,Kitakyushu,Japan","Graduate School of Information, Production and Systems, Waseda University, Kitakyushu, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Graduate School of Information, Production and Systems,Kitakyushu,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Graduate School of Information, Production and Systems, Waseda University, Kitakyushu, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056129529","display_name":"Jingdong Chen","orcid":"https://orcid.org/0000-0003-0083-9247"},"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":"Jingdong Chen","raw_affiliation_strings":["Northwestern Polytechnical University,Center of Intelligent Acoustics and Immersive Communications,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Center of Intelligent Acoustics and Immersive Communications,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5106698171"],"corresponding_institution_ids":["https://openalex.org/I150744194","https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":1.1206,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7443915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"786","last_page":"790"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9991000294685364,"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":0.9990000128746033,"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/panning","display_name":"Panning (audio)","score":0.9090244174003601},{"id":"https://openalex.org/keywords/stereophonic-sound","display_name":"Stereophonic sound","score":0.8742072582244873},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8402566909790039},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7010896801948547},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5715045928955078},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.557230532169342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.532346785068512},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47313064336776733},{"id":"https://openalex.org/keywords/bass","display_name":"Bass (fish)","score":0.4456685483455658},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41660216450691223},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3637703061103821},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11274349689483643},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09158322215080261}],"concepts":[{"id":"https://openalex.org/C108944566","wikidata":"https://www.wikidata.org/wiki/Q1524510","display_name":"Panning (audio)","level":4,"score":0.9090244174003601},{"id":"https://openalex.org/C140631703","wikidata":"https://www.wikidata.org/wiki/Q34678","display_name":"Stereophonic sound","level":3,"score":0.8742072582244873},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8402566909790039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7010896801948547},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5715045928955078},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.557230532169342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.532346785068512},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47313064336776733},{"id":"https://openalex.org/C2777182073","wikidata":"https://www.wikidata.org/wiki/Q1224135","display_name":"Bass (fish)","level":2,"score":0.4456685483455658},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41660216450691223},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3637703061103821},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11274349689483643},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09158322215080261},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.0},{"id":"https://openalex.org/C15336307","wikidata":"https://www.wikidata.org/wiki/Q1766051","display_name":"Lens (geology)","level":2,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C78762247","wikidata":"https://www.wikidata.org/wiki/Q1273174","display_name":"Petroleum engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2031647436","https://openalex.org/W2053528811","https://openalex.org/W2127851351","https://openalex.org/W2141411743","https://openalex.org/W2154918349","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2508884455","https://openalex.org/W2563637302","https://openalex.org/W2609317876","https://openalex.org/W2903502793","https://openalex.org/W2906214917","https://openalex.org/W2938709889","https://openalex.org/W2952218014","https://openalex.org/W2962753171","https://openalex.org/W2963698842","https://openalex.org/W2964058413","https://openalex.org/W2972411915","https://openalex.org/W3001377302","https://openalex.org/W3015199127","https://openalex.org/W3016447038","https://openalex.org/W3096408984","https://openalex.org/W3099330747","https://openalex.org/W3113792747","https://openalex.org/W3160050861","https://openalex.org/W3199957557","https://openalex.org/W3213726885","https://openalex.org/W3216004336","https://openalex.org/W4225311783","https://openalex.org/W4226221107","https://openalex.org/W4226300471","https://openalex.org/W4286980120","https://openalex.org/W4293518551","https://openalex.org/W4372260250","https://openalex.org/W4372260557","https://openalex.org/W4372348046","https://openalex.org/W4375928773","https://openalex.org/W4385822305","https://openalex.org/W6675574810","https://openalex.org/W6751356808","https://openalex.org/W6757632829","https://openalex.org/W6773772901","https://openalex.org/W6801426729","https://openalex.org/W6804608017","https://openalex.org/W6810984764"],"related_works":["https://openalex.org/W2154409727","https://openalex.org/W2035723688","https://openalex.org/W2069535234","https://openalex.org/W2623418588","https://openalex.org/W3094316140","https://openalex.org/W2898104624","https://openalex.org/W3133205200","https://openalex.org/W2898145319","https://openalex.org/W4289363934","https://openalex.org/W2098101267"],"abstract_inverted_index":{"Stereophonic":[0],"music":[1,20,43],"source":[2,11,82],"separation":[3],"(MSS)":[4],"is":[5],"a":[6,18,58,63],"problem":[7],"of":[8,79,87,119],"extracting":[9],"individual":[10],"tracks,":[12],"e.g.":[13],"bass,":[14],"drums,":[15],"vocals,":[16],"from":[17],"stereo":[19,42],"recording.":[21],"Deep":[22],"neural":[23,66],"network":[24,67],"(DNN)":[25],"based":[26],"MSS":[27,60],"systems":[28,52,115],"have":[29,44],"demonstrated":[30],"great":[31],"promise":[32],"though":[33],"spatial":[34,71,76,121],"panning":[35,77],"cues":[36],"and":[37,53,72,125],"time-frequency":[38,93],"spectral":[39,73,123],"structures":[40],"in":[41,50],"not":[45],"yet":[46],"been":[47],"fully":[48],"explored":[49],"such":[51],"methods.":[54],"This":[55],"paper":[56],"presents":[57],"spatially-informed":[59],"method":[61,110],"using":[62,120],"bridging":[64],"band-split":[65],"that":[68,107],"incorporates":[69],"both":[70],"information.":[74],"The":[75],"angles":[78],"each":[80],"target":[81],"are":[83,99],"used":[84],"as":[85,116],"input":[86],"the":[88,92,96,108,113,117],"network,":[89],"along":[90],"with":[91],"spectrograms.":[94],"Moreover,":[95],"inter-track":[97,126],"correlations":[98],"exploited":[100],"for":[101],"further":[102],"performance":[103],"improvement.":[104],"Experiments":[105],"show":[106],"proposed":[109],"outperforms":[111],"significantly":[112],"baseline":[114],"result":[118],"cues,":[122],"characteristics,":[124],"relationships.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
