{"id":"https://openalex.org/W2771678900","doi":"https://doi.org/10.1109/waspaa.2017.8169995","title":"Guiding audio source separation by video object information","display_name":"Guiding audio source separation by video object information","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2771678900","doi":"https://doi.org/10.1109/waspaa.2017.8169995","mag":"2771678900"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2017.8169995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2017.8169995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"preprint","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/A5001145583","display_name":"Sanjeel Parekh","orcid":"https://orcid.org/0000-0002-2251-7436"},"institutions":[{"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/I4210121266","display_name":"Technicolor (France)","ror":"https://ror.org/02ya5n776","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210121266"]},{"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/I4210145102","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Sanjeel Parekh","raw_affiliation_strings":["LTCI, Universit\u00e9 Paris-Saclay, Paris, France","Technicolor, Cesson S\u00e9vign\u00e9, France"],"affiliations":[{"raw_affiliation_string":"LTCI, Universit\u00e9 Paris-Saclay, Paris, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4210165912"]},{"raw_affiliation_string":"Technicolor, Cesson S\u00e9vign\u00e9, France","institution_ids":["https://openalex.org/I4210121266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060031161","display_name":"Slim Essid","orcid":"https://orcid.org/0000-0002-0028-327X"},"institutions":[{"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/I4210145102","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]},{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Slim Essid","raw_affiliation_strings":["LTCI, Universit\u00e9 Paris-Saclay, Paris, France"],"affiliations":[{"raw_affiliation_string":"LTCI, Universit\u00e9 Paris-Saclay, Paris, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073788938","display_name":"Alexey Ozerov","orcid":"https://orcid.org/0000-0003-4834-5166"},"institutions":[{"id":"https://openalex.org/I4210121266","display_name":"Technicolor (France)","ror":"https://ror.org/02ya5n776","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210121266"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alexey Ozerov","raw_affiliation_strings":["Technicolor, Cesson S\u00e9vign\u00e9, France"],"affiliations":[{"raw_affiliation_string":"Technicolor, Cesson S\u00e9vign\u00e9, France","institution_ids":["https://openalex.org/I4210121266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041584595","display_name":"Ngoc Q. K. Duong","orcid":"https://orcid.org/0000-0002-7627-8194"},"institutions":[{"id":"https://openalex.org/I4210121266","display_name":"Technicolor (France)","ror":"https://ror.org/02ya5n776","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210121266"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ngoc Q. K. Duong","raw_affiliation_strings":["Technicolor, Cesson S\u00e9vign\u00e9, France"],"affiliations":[{"raw_affiliation_string":"Technicolor, Cesson S\u00e9vign\u00e9, France","institution_ids":["https://openalex.org/I4210121266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076170578","display_name":"Patrick P\u00e9rez","orcid":"https://orcid.org/0000-0002-8124-1206"},"institutions":[{"id":"https://openalex.org/I4210121266","display_name":"Technicolor (France)","ror":"https://ror.org/02ya5n776","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210121266"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Patrick Perez","raw_affiliation_strings":["Technicolor, Cesson S\u00e9vign\u00e9, France"],"affiliations":[{"raw_affiliation_string":"Technicolor, Cesson S\u00e9vign\u00e9, France","institution_ids":["https://openalex.org/I4210121266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055423112","display_name":"Ga\u00ebl Richard","orcid":"https://orcid.org/0000-0002-4960-0010"},"institutions":[{"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/I4210145102","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]},{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gael Richard","raw_affiliation_strings":["LTCI, Universit\u00e9 Paris-Saclay, Paris, France"],"affiliations":[{"raw_affiliation_string":"LTCI, Universit\u00e9 Paris-Saclay, Paris, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4210165912"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001145583"],"corresponding_institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4210121266","https://openalex.org/I4210165912"],"apc_list":null,"apc_paid":null,"fwci":1.41646489,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.82251381,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"61","last_page":"65"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.9977999925613403,"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/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.8408303260803223},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8167542219161987},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7863143682479858},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.6475616693496704},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5839069485664368},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5692812204360962},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5584039092063904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5162496566772461},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4804234504699707},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.46943143010139465},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.4639890193939209},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4248868525028229},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39370572566986084},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36780697107315063},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07815513014793396}],"concepts":[{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8408303260803223},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8167542219161987},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7863143682479858},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.6475616693496704},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5839069485664368},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5692812204360962},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5584039092063904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5162496566772461},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4804234504699707},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.46943143010139465},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.4639890193939209},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4248868525028229},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39370572566986084},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36780697107315063},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07815513014793396},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa.2017.8169995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2017.8169995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1486994328","https://openalex.org/W1931249336","https://openalex.org/W1963859670","https://openalex.org/W2017548439","https://openalex.org/W2031647436","https://openalex.org/W2043095867","https://openalex.org/W2106488367","https://openalex.org/W2114508388","https://openalex.org/W2127851351","https://openalex.org/W2135029798","https://openalex.org/W2167353662","https://openalex.org/W2168010845","https://openalex.org/W2168509488","https://openalex.org/W2168818958","https://openalex.org/W2171819471","https://openalex.org/W2197046994","https://openalex.org/W2381486035","https://openalex.org/W2562551209","https://openalex.org/W2564082645","https://openalex.org/W2644497536","https://openalex.org/W3143596294","https://openalex.org/W4285719527","https://openalex.org/W6628900912","https://openalex.org/W6675974536","https://openalex.org/W6680012447","https://openalex.org/W6684447540","https://openalex.org/W6731354787","https://openalex.org/W7071105756"],"related_works":["https://openalex.org/W2037504162","https://openalex.org/W2774154397","https://openalex.org/W2146544734","https://openalex.org/W2921513691","https://openalex.org/W2156699640","https://openalex.org/W2098101267","https://openalex.org/W1979654135","https://openalex.org/W2156181515","https://openalex.org/W1984255382","https://openalex.org/W2576645943"],"abstract_inverted_index":{"In":[0],"this":[1],"work":[2,60],"we":[3,40],"propose":[4],"novel":[5],"joint":[6],"and":[7,52,68],"sequential":[8],"multimodal":[9,78],"approaches":[10],"for":[11],"the":[12,26,35,89],"task":[13],"of":[14,80],"single":[15],"channel":[16],"audio":[17,53],"source":[18,66],"separation":[19,67],"in":[20],"videos.":[21],"This":[22],"is":[23],"done":[24],"within":[25],"popular":[27],"non-negative":[28,45],"matrix":[29],"factorization":[30],"framework":[31],"using":[32],"information":[33],"about":[34],"sounding":[36],"object's":[37],"motion.":[38],"Specifically,":[39],"present":[41],"methods":[42],"that":[43],"utilize":[44],"least":[46],"squares":[47],"formulation":[48],"to":[49,71],"couple":[50],"motion":[51],"information.":[54],"The":[55],"proposed":[56],"techniques":[57],"generalize":[58],"recent":[59],"carried":[61],"out":[62],"on":[63],"NMF-based":[64],"motion-informed":[65],"easily":[69],"extend":[70],"video":[72],"data.":[73],"Experiments":[74],"with":[75],"two":[76],"distinct":[77],"datasets":[79],"string":[81],"instrument":[82],"performance":[83],"recordings":[84],"illustrate":[85],"their":[86],"advantages":[87],"over":[88],"existing":[90],"methods.":[91]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}