{"id":"https://openalex.org/W2151155390","doi":"https://doi.org/10.1109/mmsp.2004.1436412","title":"Using audiovisual speech processing to improve the robustness of the separation of convolutive speech mixtures","display_name":"Using audiovisual speech processing to improve the robustness of the separation of convolutive speech mixtures","publication_year":2005,"publication_date":"2005-06-07","ids":{"openalex":"https://openalex.org/W2151155390","doi":"https://doi.org/10.1109/mmsp.2004.1436412","mag":"2151155390"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2004.1436412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2004.1436412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE 6th Workshop on Multimedia Signal Processing, 2004.","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/A5071156904","display_name":"Bertrand Rivet","orcid":"https://orcid.org/0000-0003-4901-5302"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"B. Rivet","raw_affiliation_strings":["Speech Commun. Inst., Grenoble Nat. Polytech Inst., France"],"affiliations":[{"raw_affiliation_string":"Speech Commun. Inst., Grenoble Nat. Polytech Inst., France","institution_ids":[]}]},{"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/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"L. Girin","raw_affiliation_strings":["Speech Communication Institute (ICP), National Polytechnic Institute of Grenoble, Grenoble, France"],"affiliations":[{"raw_affiliation_string":"Speech Communication Institute (ICP), National Polytechnic Institute of Grenoble, Grenoble, France","institution_ids":["https://openalex.org/I106785703"]}]},{"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/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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"C. Jutten","raw_affiliation_strings":["Image and Signal Processing Laboratory(LIS), National Polytechnic Institute of Grenoble, Grenoble, France"],"affiliations":[{"raw_affiliation_string":"Image and Signal Processing Laboratory(LIS), National Polytechnic Institute of Grenoble, Grenoble, France","institution_ids":["https://openalex.org/I4210114274"]}]},{"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/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"J. Schwartz","raw_affiliation_strings":["Speech Communication Institute (ICP), National Polytechnic Institute of Grenoble, Grenoble, France"],"affiliations":[{"raw_affiliation_string":"Speech Communication Institute (ICP), National Polytechnic Institute of Grenoble, Grenoble, France","institution_ids":["https://openalex.org/I106785703"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5071156904"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9538,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77130704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"47","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","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/T11447","display_name":"Blind Source Separation Techniques","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/T10860","display_name":"Speech 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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9965000152587891,"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":0.7294303774833679},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7223918437957764},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7081985473632812},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.6537342071533203},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5651126503944397},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.5626963376998901},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.48522305488586426},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4752359390258789},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4675746262073517},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.36030593514442444},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33530282974243164},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32671958208084106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32159045338630676},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.1565636396408081},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09385547041893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7294303774833679},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7223918437957764},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7081985473632812},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.6537342071533203},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5651126503944397},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.5626963376998901},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.48522305488586426},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4752359390258789},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4675746262073517},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.36030593514442444},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33530282974243164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32671958208084106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32159045338630676},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.1565636396408081},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09385547041893005},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp.2004.1436412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2004.1436412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE 6th Workshop on Multimedia Signal Processing, 2004.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W335832833","https://openalex.org/W1548802052","https://openalex.org/W1573024203","https://openalex.org/W1989581163","https://openalex.org/W2010929291","https://openalex.org/W2038010270","https://openalex.org/W2049633694","https://openalex.org/W2098717567","https://openalex.org/W2119647652","https://openalex.org/W2127211243","https://openalex.org/W2153639013","https://openalex.org/W2405539902","https://openalex.org/W4205778870","https://openalex.org/W6611594693","https://openalex.org/W6634352053"],"related_works":["https://openalex.org/W1509813908","https://openalex.org/W2166132814","https://openalex.org/W1005611038","https://openalex.org/W2031820693","https://openalex.org/W3024816962","https://openalex.org/W973023320","https://openalex.org/W1910172735","https://openalex.org/W2118307209","https://openalex.org/W2107364365","https://openalex.org/W2539388437"],"abstract_inverted_index":{"Looking":[0],"at":[1,99],"the":[2,17,48,59,64,87,94,100,103,118],"speaker's":[3],"face":[4],"seems":[5],"useful":[6],"in":[7,47,58,117],"hearing":[8],"better":[9],"a":[10,27],"speech":[11,34],"signal":[12],"and":[13,86],"extract":[14],"it":[15],"from":[16],"competing":[18],"sources":[19],"before":[20],"identification.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25],"present":[26],"novel":[28],"algorithm":[29,55],"plugging":[30],"audiovisual":[31,88],"coherence":[32],"of":[33,51,102,120],"signals,":[35],"estimated":[36],"by":[37,76,81],"statistical":[38],"tools,":[39],"on":[40],"audio":[41,83],"blind":[42],"source":[43,96],"separation":[44,78,104],"(BSS)":[45],"algorithms":[46],"difficult":[49],"case":[50,119],"convolutive":[52,65,125],"mixtures.":[53,126],"The":[54,109],"mainly":[56],"works":[57],"frequency":[60,73,77],"(transform)":[61],"domain,":[62],"where":[63],"mixture":[66,70],"becomes":[67],"an":[68,82],"additive":[69],"for":[71,106],"each":[72,107],"channel.":[74],"Frequency":[75],"is":[79,90,112],"made":[80],"BSS":[84],"algorithm,":[85],"information":[89],"used":[91],"to":[92,114],"solve":[93],"standard":[95],"permutation":[97],"problem":[98],"output":[101],"stage,":[105],"frequency.":[108],"proposed":[110],"method":[111],"shown":[113],"be":[115],"efficient":[116],"2":[121,124],"/spl":[122],"times/":[123]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
