{"id":"https://openalex.org/W2408588119","doi":"https://doi.org/10.1109/taslp.2016.2570945","title":"Projection-Based Demixing of Spatial Audio","display_name":"Projection-Based Demixing of Spatial Audio","publication_year":2016,"publication_date":"2016-05-20","ids":{"openalex":"https://openalex.org/W2408588119","doi":"https://doi.org/10.1109/taslp.2016.2570945","mag":"2408588119"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2570945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2570945","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5027353739","display_name":"Derry Fitzgerald","orcid":"https://orcid.org/0000-0001-8057-858X"},"institutions":[{"id":"https://openalex.org/I4210100923","display_name":"Munster Technological University","ror":"https://ror.org/013xpqh61","country_code":"IE","type":"facility","lineage":["https://openalex.org/I4210100923"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Derry FitzGerald","raw_affiliation_strings":["Cork School of Music, Cork Institute of Technology, Cork, Ireland","NIMBUS - NIMBUS Centre [Cork] (Cork Institute of Technology Campus, Bishopstown, Cork - Ireland)"],"raw_orcid":"https://orcid.org/0000-0001-8057-858X","affiliations":[{"raw_affiliation_string":"Cork School of Music, Cork Institute of Technology, Cork, Ireland","institution_ids":["https://openalex.org/I4210100923"]},{"raw_affiliation_string":"NIMBUS - NIMBUS Centre [Cork] (Cork Institute of Technology Campus, Bishopstown, Cork - Ireland)","institution_ids":["https://openalex.org/I4210100923"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012543477","display_name":"Antoine Liutkus","orcid":"https://orcid.org/0000-0002-3458-6498"},"institutions":[{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I4210127166","display_name":"Centre Inria de l'Universit\u00e9 de Lorraine","ror":"https://ror.org/03fcjvn64","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210127166"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Liutkus","raw_affiliation_strings":["Inria, Nancy Grand-Est, Multispeech Team, LORIA UMR\u00a07503, Universit\u00e9 de Lorraine, Nancy, France","MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, Nancy Grand-Est, Multispeech Team, LORIA UMR\u00a07503, Universit\u00e9 de Lorraine, Nancy, France","institution_ids":["https://openalex.org/I4210121838","https://openalex.org/I4210127166","https://openalex.org/I90183372"]},{"raw_affiliation_string":"MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028865449","display_name":"Roland Badeau","orcid":"https://orcid.org/0000-0002-9630-6877"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Roland Badeau","raw_affiliation_strings":["LTCI, CNRS, T\u00e9l\u00e9com ParisTech, Universit\u00e9 Paris-Saclay, Paris, France","LTCI - Laboratoire Traitement et Communication de l'Information (46 rue Barrault F-75634 Paris Cedex 13 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, CNRS, T\u00e9l\u00e9com ParisTech, Universit\u00e9 Paris-Saclay, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4210165912"]},{"raw_affiliation_string":"LTCI - Laboratoire Traitement et Communication de l'Information (46 rue Barrault F-75634 Paris Cedex 13 - France)","institution_ids":["https://openalex.org/I4210165912"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.234,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.92138365,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"24","issue":"9","first_page":"1560","last_page":"1572"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9991999864578247,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7385208606719971},{"id":"https://openalex.org/keywords/stereophonic-sound","display_name":"Stereophonic sound","score":0.7148560881614685},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6043024659156799},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.568888783454895},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.4711792767047882},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4607999622821808},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4541555941104889},{"id":"https://openalex.org/keywords/superposition-principle","display_name":"Superposition principle","score":0.43958431482315063},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4357214570045471},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.43524011969566345},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.43431392312049866},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.4259181618690491},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.42449378967285156},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38079607486724854},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36930131912231445},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3092226982116699},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18686124682426453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7385208606719971},{"id":"https://openalex.org/C140631703","wikidata":"https://www.wikidata.org/wiki/Q34678","display_name":"Stereophonic sound","level":3,"score":0.7148560881614685},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6043024659156799},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.568888783454895},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.4711792767047882},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4607999622821808},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4541555941104889},{"id":"https://openalex.org/C27753989","wikidata":"https://www.wikidata.org/wiki/Q284885","display_name":"Superposition principle","level":2,"score":0.43958431482315063},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4357214570045471},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.43524011969566345},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.43431392312049866},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4259181618690491},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.42449378967285156},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38079607486724854},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36930131912231445},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3092226982116699},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18686124682426453},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2016.2570945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2570945","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-01260588v2","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-01260588","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Audio, Speech and Language Processing, 2016, &#x27E8;10.1109/TASLP.2016.2570945&#x27E9;","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4728815296","display_name":"Editing and Rendering for next generation of 3D sound","funder_award_id":"ANR-13-CORD-0008","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5012497482","display_name":"Creative Dynamics of Improvised Interaction","funder_award_id":"ANR-14-CE24-0002","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G6992485691","display_name":"Online unmixing for large historical archives","funder_award_id":"ANR-15-CE38-0003","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W68855703","https://openalex.org/W83793253","https://openalex.org/W186036538","https://openalex.org/W192032276","https://openalex.org/W1246381107","https://openalex.org/W1484664922","https://openalex.org/W1491186237","https://openalex.org/W1529883046","https://openalex.org/W1539480699","https://openalex.org/W1540920731","https://openalex.org/W1541169733","https://openalex.org/W1545766482","https://openalex.org/W1580960963","https://openalex.org/W1965586400","https://openalex.org/W1973450013","https://openalex.org/W1974186229","https://openalex.org/W1981755271","https://openalex.org/W1984255382","https://openalex.org/W1986205059","https://openalex.org/W1987906574","https://openalex.org/W2008565517","https://openalex.org/W2021196544","https://openalex.org/W2022894179","https://openalex.org/W2039844283","https://openalex.org/W2043532615","https://openalex.org/W2072503712","https://openalex.org/W2098101267","https://openalex.org/W2099398754","https://openalex.org/W2102820094","https://openalex.org/W2108494558","https://openalex.org/W2112728813","https://openalex.org/W2113990625","https://openalex.org/W2114508388","https://openalex.org/W2117155634","https://openalex.org/W2127462062","https://openalex.org/W2127851351","https://openalex.org/W2128055577","https://openalex.org/W2135029798","https://openalex.org/W2143027228","https://openalex.org/W2149273154","https://openalex.org/W2160697975","https://openalex.org/W2161796871","https://openalex.org/W2162514423","https://openalex.org/W2164074203","https://openalex.org/W2167353662","https://openalex.org/W2168273590","https://openalex.org/W2267665870","https://openalex.org/W3143596294","https://openalex.org/W3152035499","https://openalex.org/W4246756383","https://openalex.org/W4301970831","https://openalex.org/W6603409251","https://openalex.org/W6607619696","https://openalex.org/W6607733836","https://openalex.org/W6629509115","https://openalex.org/W6632199626","https://openalex.org/W6632596619","https://openalex.org/W6634984501","https://openalex.org/W6643542218","https://openalex.org/W6678885621","https://openalex.org/W6680012447","https://openalex.org/W6693386753"],"related_works":["https://openalex.org/W2903715697","https://openalex.org/W2002471218","https://openalex.org/W2157715557","https://openalex.org/W2069535234","https://openalex.org/W2401610501","https://openalex.org/W2098446659","https://openalex.org/W2766254947","https://openalex.org/W165956390","https://openalex.org/W2790858698","https://openalex.org/W2810739589"],"abstract_inverted_index":{"We":[0],"propose":[1,187],"a":[2,25,28,66,119,213],"method":[3,185,244],"to":[4,56,117,122,178,197,228],"unmix":[5],"multichannel":[6,203],"audio":[7,21,233],"signals":[8,102],"into":[9],"their":[10],"different":[11,80,231],"constitutive":[12],"spatial":[13,26,35,232],"objects.":[14],"To":[15],"achieve":[16],"this,":[17],"we":[18,37,165,186,224],"characterize":[19],"an":[20,44,129],"object":[22,45,72,130],"through":[23],"both":[24],"and":[27,69,83,124,183],"spectro-temporal":[29,87],"modeling.":[30],"The":[31],"particularity":[32],"of":[33,76,113,128,134,171,209,242,250],"the":[34,58,74,93,110,132,137,172,180,184,191,201,210,230,243,248],"model":[36,57,89,181],"pick":[38],"is":[39,90,116,151,245],"that":[40],"it":[41,54,63],"neither":[42],"assumes":[43],"has":[46],"only":[47],"one":[48],"underlying":[49],"source":[50],"point,":[51],"nor":[52],"does":[53],"attempt":[55],"complex":[59],"room":[60],"acoustics.":[61],"Instead,":[62,164],"focuses":[64],"on":[65,92,146,194,247],"listener":[67],"perspective,":[68],"takes":[70],"each":[71,206],"as":[73,107],"superposition":[75],"many":[77,195],"contributions":[78],"with":[79,103],"incoming":[81],"directions":[82],"interchannel":[84,126],"delays.":[85],"Our":[86],"probabilistic":[88],"based":[91,193],"recently":[94],"proposed":[95],"\u03b1-harmonisable":[96],"processes,":[97],"which":[98],"are":[99,161,219],"adequate":[100],"for":[101,131,155,200],"large":[104],"dynamics,":[105],"such":[106,207],"audio.":[108,204],"Then,":[109],"main":[111],"originality":[112],"this":[114],"paper":[115],"provide":[118],"new":[120,214],"way":[121],"estimate":[123],"exploit":[125],"dependences":[127],"purpose":[133],"demixing.":[135],"In":[136],"Gaussian":[138],"\u03b1":[139,156],"=":[140],"2":[141,158],"case,":[142],"previous":[143],"research":[144],"focused":[145],"covariance":[147],"structures.":[148],"This":[149],"approach":[150],"no":[152],"longer":[153],"valid":[154],"<;":[157],"where":[159,216],"covariances":[160],"not":[162],"defined.":[163],"show":[166],"how":[167,227],"simple":[168],"linear":[169],"combinations":[170],"mixture":[173,211],"channels":[174],"can":[175],"be":[176],"used":[177],"learn":[179],"parameters,":[182],"consists":[188],"in":[189],"pooling":[190],"estimates":[192],"projections":[196],"correctly":[198],"account":[199],"original":[202],"Intuitively,":[205],"downmix":[208],"provides":[212],"perspective":[215],"some":[217],"objects":[218,234],"canceled":[220],"or":[221],"enhanced.":[222],"Finally,":[223],"also":[225],"explain":[226],"recover":[229],"when":[235],"all":[236],"parameters":[237],"have":[238],"been":[239],"computed.":[240],"Performance":[241],"illustrated":[246],"separation":[249],"stereophonic":[251],"music":[252],"signals.":[253]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":7}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}