{"id":"https://openalex.org/W2033777071","doi":"https://doi.org/10.1109/isspa.2003.1224816","title":"Speech extraction based on ICA and audio-visual coherence","display_name":"Speech extraction based on ICA and audio-visual coherence","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2033777071","doi":"https://doi.org/10.1109/isspa.2003.1224816","mag":"2033777071"},"language":"en","primary_location":{"id":"doi:10.1109/isspa.2003.1224816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspa.2003.1224816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","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/A5087166091","display_name":"David Sodoyer","orcid":"https://orcid.org/0000-0001-9081-3950"},"institutions":[{"id":"https://openalex.org/I36085230","display_name":"Universit\u00e9 Stendhal \u2013 Grenoble 3","ror":"https://ror.org/03yppfm65","country_code":"FR","type":"education","lineage":["https://openalex.org/I36085230","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"D. Sodoyer","raw_affiliation_strings":["Speech Communication Institute (ICP), CMS UMR 5009, INPG, Universit\u00e9 Stendhal, Grenoble, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Communication Institute (ICP), CMS UMR 5009, INPG, Universit\u00e9 Stendhal, Grenoble, France","institution_ids":["https://openalex.org/I36085230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020392160","display_name":"Laurent Girin","orcid":"https://orcid.org/0000-0002-9214-8760"},"institutions":[{"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/I36085230","display_name":"Universit\u00e9 Stendhal \u2013 Grenoble 3","ror":"https://ror.org/03yppfm65","country_code":"FR","type":"education","lineage":["https://openalex.org/I36085230","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"L. Girin","raw_affiliation_strings":["Speech Communication Institute (ICP), CNRS UMR 5009, INPG, Universit\u00e9 Stendhal, Grenoble, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Communication Institute (ICP), CNRS UMR 5009, INPG, Universit\u00e9 Stendhal, Grenoble, France","institution_ids":["https://openalex.org/I36085230","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055562421","display_name":"Christian Jutten","orcid":"https://orcid.org/0000-0002-4477-4847"},"institutions":[{"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/I177483745","display_name":"Universit\u00e9 Joseph Fourier","ror":"https://ror.org/02aj0kh94","country_code":"FR","type":"education","lineage":["https://openalex.org/I177483745"]},{"id":"https://openalex.org/I36085230","display_name":"Universit\u00e9 Stendhal \u2013 Grenoble 3","ror":"https://ror.org/03yppfm65","country_code":"FR","type":"education","lineage":["https://openalex.org/I36085230","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I4210114274","display_name":"Laboratoire d\u2019Informatique et Syst\u00e8mes","ror":"https://ror.org/0257sgk90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I143002897","https://openalex.org/I21491767","https://openalex.org/I4210114274"]},{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"C. Jutten","raw_affiliation_strings":["Image and Signal Processing Laboratory (LIS), CNRS UMR 5083. INPG, UJF, Grenoble, France","Speech Communication Institute (ICP), CMS UMR 5009, INPG, Universit\u00e9 Stendhal, Grenoble, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Image and Signal Processing Laboratory (LIS), CNRS UMR 5083. INPG, UJF, Grenoble, France","institution_ids":["https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I177483745","https://openalex.org/I4210114274","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Speech Communication Institute (ICP), CMS UMR 5009, INPG, Universit\u00e9 Stendhal, Grenoble, France","institution_ids":["https://openalex.org/I36085230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001142101","display_name":"Jean\u2010Luc Schwartz","orcid":"https://orcid.org/0000-0001-8969-9185"},"institutions":[{"id":"https://openalex.org/I36085230","display_name":"Universit\u00e9 Stendhal \u2013 Grenoble 3","ror":"https://ror.org/03yppfm65","country_code":"FR","type":"education","lineage":["https://openalex.org/I36085230","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"J.-L. Schwartz","raw_affiliation_strings":["Speech Communication Institute (ICP), CMS UMR 5009, INPG, Universit\u00e9 Stendhal, Grenoble, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Communication Institute (ICP), CMS UMR 5009, INPG, Universit\u00e9 Stendhal, Grenoble, France","institution_ids":["https://openalex.org/I36085230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2966,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.56740196,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"109","issue":null,"first_page":"65","last_page":"68 vol.2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","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/T11447","display_name":"Blind Source Separation Techniques","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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9959999918937683,"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":0.7760758399963379},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7483422160148621},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.7233279347419739},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5380155444145203},{"id":"https://openalex.org/keywords/independent-component-analysis","display_name":"Independent component analysis","score":0.5260657668113708},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5179464221000671},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4913894236087799},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48740461468696594},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.48125144839286804},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.474723219871521},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.46584710478782654},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4251343607902527},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4238923192024231},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4189662039279938},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4117470979690552},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2767176628112793},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1343921422958374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7760758399963379},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7483422160148621},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.7233279347419739},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5380155444145203},{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.5260657668113708},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5179464221000671},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4913894236087799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48740461468696594},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.48125144839286804},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.474723219871521},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.46584710478782654},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4251343607902527},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4238923192024231},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4189662039279938},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4117470979690552},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2767176628112793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1343921422958374},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isspa.2003.1224816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspa.2003.1224816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W335832833","https://openalex.org/W1488183088","https://openalex.org/W1977067929","https://openalex.org/W2038010270","https://openalex.org/W2124757684","https://openalex.org/W2127211243","https://openalex.org/W2135081730","https://openalex.org/W6659817735"],"related_works":["https://openalex.org/W2390344110","https://openalex.org/W2364896863","https://openalex.org/W2361066326","https://openalex.org/W2046761971","https://openalex.org/W2107364365","https://openalex.org/W2118307209","https://openalex.org/W1785857632","https://openalex.org/W4281722104","https://openalex.org/W2187523794","https://openalex.org/W1503525627"],"abstract_inverted_index":{"We":[0,45],"present":[1],"a":[2,47],"new":[3],"approach":[4],"to":[5,26],"the":[6,15,20,23,41,51,62,87,95],"source":[7],"separation":[8,66],"problem":[9],"for":[10,60],"multiple":[11],"speech":[12,30],"signals.":[13],"Using":[14],"extra":[16],"visual":[17,55],"information":[18],"of":[19,50,54,79],"speaker's":[21,42],"face,":[22],"method":[24],"aims":[25],"extract":[27],"an":[28],"acoustic":[29,34],"signal":[31],"from":[32],"other":[33],"signals":[35],"by":[36,70],"exploiting":[37],"its":[38],"coherence":[39],"with":[40],"lip":[43],"movements.":[44],"define":[46],"statistical":[48],"model":[49],"joint":[52,73],"probability":[53],"and":[56,82,91],"spectral":[57],"audio":[58],"input":[59],"quantifying":[61],"audio-visual":[63],"coherence.":[64],"Then,":[65],"can":[67],"be":[68],"achieved":[69],"maximising":[71],"this":[72],"probability.":[74],"Experiments":[75],"on":[76],"additive":[77],"mixtures":[78],"2,":[80],"3":[81],"5":[83],"sources":[84],"show":[85],"that":[86],"algorithm":[88,98],"performs":[89],"well,":[90],"systematically":[92],"better":[93],"than":[94],"classical":[96],"BSS":[97],"JADE.":[99]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
