{"id":"https://openalex.org/W2169491631","doi":"https://doi.org/10.1109/tnn.2009.2032182","title":"Learning Bimodal Structure in Audio\u2013Visual Data","display_name":"Learning Bimodal Structure in Audio\u2013Visual Data","publication_year":2009,"publication_date":"2009-10-08","ids":{"openalex":"https://openalex.org/W2169491631","doi":"https://doi.org/10.1109/tnn.2009.2032182","mag":"2169491631","pmid":"https://pubmed.ncbi.nlm.nih.gov/19963447"},"language":"en","primary_location":{"id":"doi:10.1109/tnn.2009.2032182","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnn.2009.2032182","pdf_url":null,"source":{"id":"https://openalex.org/S42080949","display_name":"IEEE Transactions on Neural Networks","issn_l":"1045-9227","issn":["1045-9227","1941-0093"],"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 Transactions on Neural Networks","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/125304","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077875525","display_name":"Gianluca Monaci","orcid":"https://orcid.org/0000-0001-5514-8457"},"institutions":[{"id":"https://openalex.org/I4210122849","display_name":"Philips (Netherlands)","ror":"https://ror.org/02p2bgp27","country_code":"NL","type":"company","lineage":["https://openalex.org/I4210122849"]},{"id":"https://openalex.org/I4210145836","display_name":"Center for Theoretical Biological Physics","ror":"https://ror.org/04hfg7v94","country_code":"US","type":"facility","lineage":["https://openalex.org/I12912129","https://openalex.org/I181547552","https://openalex.org/I2801539370","https://openalex.org/I4210145836","https://openalex.org/I44461941","https://openalex.org/I74775410"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["NL","US"],"is_corresponding":false,"raw_author_name":"G. Monaci","raw_affiliation_strings":["Redwood Center for Theoretical Neuroscience, University of California, Berkeley, CA 94720-3190 USA. gianluca.monaci@philips.com","Redwood Center of Theoretical Neuroscience, University of California, Berkeley, CA, USA","Video Processing and Analysis Group, Philips Research Laboratories, Eindhoven, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Redwood Center for Theoretical Neuroscience, University of California, Berkeley, CA 94720-3190 USA. gianluca.monaci@philips.com","institution_ids":["https://openalex.org/I4210145836"]},{"raw_affiliation_string":"Redwood Center of Theoretical Neuroscience, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Video Processing and Analysis Group, Philips Research Laboratories, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I4210122849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028520858","display_name":"Pierre Vandergheynst","orcid":"https://orcid.org/0000-0002-9070-900X"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"P. Vandergheynst","raw_affiliation_strings":["Institute of Electrical Engineering, Ecole Polytechnique Federale de Lausanne, Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electrical Engineering, Ecole Polytechnique Federale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085896415","display_name":"Friedrich T. Sommer","orcid":"https://orcid.org/0000-0002-6738-9263"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"F.T. Sommer","raw_affiliation_strings":["Redwood Center of Theoretical Neuroscience, University of California, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Redwood Center of Theoretical Neuroscience, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9355,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.95546286,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"20","issue":"12","first_page":"1898","last_page":"1910"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","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/T10860","display_name":"Speech and Audio Processing","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/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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":0.9976999759674072,"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":0.7267981767654419},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6356605291366577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6155826449394226},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5987908840179443},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5316919088363647},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5260279774665833},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5118357539176941},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.49101948738098145},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.47855693101882935},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.45678576827049255},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4423767626285553},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.42694002389907837},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3353234529495239},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.19545546174049377},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13501805067062378}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7267981767654419},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6356605291366577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6155826449394226},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5987908840179443},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5316919088363647},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5260279774665833},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5118357539176941},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.49101948738098145},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.47855693101882935},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.45678576827049255},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4423767626285553},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.42694002389907837},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3353234529495239},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.19545546174049377},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13501805067062378},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000161","descriptor_name":"Acoustic Stimulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000161","descriptor_name":"Acoustic Stimulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000161","descriptor_name":"Acoustic Stimulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001307","descriptor_name":"Auditory Perception","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D001307","descriptor_name":"Auditory Perception","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D001307","descriptor_name":"Auditory Perception","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004193","descriptor_name":"Discrimination Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004193","descriptor_name":"Discrimination Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004193","descriptor_name":"Discrimination Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D010775","descriptor_name":"Photic Stimulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010775","descriptor_name":"Photic Stimulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010775","descriptor_name":"Photic Stimulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014796","descriptor_name":"Visual Perception","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D014796","descriptor_name":"Visual Perception","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D014796","descriptor_name":"Visual Perception","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D021641","descriptor_name":"Recognition, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021641","descriptor_name":"Recognition, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021641","descriptor_name":"Recognition, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1109/tnn.2009.2032182","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnn.2009.2032182","pdf_url":null,"source":{"id":"https://openalex.org/S42080949","display_name":"IEEE Transactions on Neural Networks","issn_l":"1045-9227","issn":["1045-9227","1941-0093"],"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 Transactions on Neural Networks","raw_type":"journal-article"},{"id":"pmid:19963447","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19963447","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.167.1901","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.167.1901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/125304/files/IEEETNN_final.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:125304","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/125304","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.tind.io:125304","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/26539","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"research article"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:125304","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/125304","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W95696665","https://openalex.org/W1485280399","https://openalex.org/W1496441095","https://openalex.org/W1537155450","https://openalex.org/W1570419640","https://openalex.org/W1576854369","https://openalex.org/W1964901013","https://openalex.org/W1974774078","https://openalex.org/W1986931325","https://openalex.org/W1996803179","https://openalex.org/W2007815184","https://openalex.org/W2015394094","https://openalex.org/W2018832332","https://openalex.org/W2021302824","https://openalex.org/W2029192628","https://openalex.org/W2031767521","https://openalex.org/W2033966334","https://openalex.org/W2065428732","https://openalex.org/W2078639319","https://openalex.org/W2095532467","https://openalex.org/W2096391593","https://openalex.org/W2099151709","https://openalex.org/W2100561338","https://openalex.org/W2104804886","https://openalex.org/W2105464873","https://openalex.org/W2108838716","https://openalex.org/W2115205382","https://openalex.org/W2115755118","https://openalex.org/W2118847468","https://openalex.org/W2119414569","https://openalex.org/W2121861296","https://openalex.org/W2122315118","https://openalex.org/W2123804611","https://openalex.org/W2129409783","https://openalex.org/W2133285226","https://openalex.org/W2139122061","https://openalex.org/W2140499889","https://openalex.org/W2142352693","https://openalex.org/W2144573398","https://openalex.org/W2144982973","https://openalex.org/W2146208719","https://openalex.org/W2147019955","https://openalex.org/W2148659689","https://openalex.org/W2149194912","https://openalex.org/W2151693816","https://openalex.org/W2153663612","https://openalex.org/W2154091569","https://openalex.org/W2154151281","https://openalex.org/W2154332973","https://openalex.org/W2160547390","https://openalex.org/W2161226030","https://openalex.org/W2162409952","https://openalex.org/W2164696938","https://openalex.org/W2164899449","https://openalex.org/W2167709189","https://openalex.org/W2169570466","https://openalex.org/W2266447120","https://openalex.org/W2278884322","https://openalex.org/W2293807473","https://openalex.org/W2552552067","https://openalex.org/W2946776431","https://openalex.org/W2963909185","https://openalex.org/W4244025079","https://openalex.org/W6614763650","https://openalex.org/W6634092760","https://openalex.org/W6675048546","https://openalex.org/W6681997382","https://openalex.org/W6682944742","https://openalex.org/W6684193366","https://openalex.org/W6766005275"],"related_works":["https://openalex.org/W2580345890","https://openalex.org/W2080322084","https://openalex.org/W2089413146","https://openalex.org/W1967456564","https://openalex.org/W2110459882","https://openalex.org/W2726222394","https://openalex.org/W2060018053","https://openalex.org/W2538748790","https://openalex.org/W4312095940","https://openalex.org/W2095296133"],"abstract_inverted_index":{"A":[0],"novel":[1],"model":[2],"is":[3,15,26,91],"presented":[4],"to":[5,67,100],"learn":[6],"bimodally":[7],"informative":[8],"structures":[9],"from":[10,73],"audio-visual":[11,22,47,74,85],"signals.":[12],"The":[13,61,76],"signal":[14],"represented":[16],"as":[17],"a":[18,27,39,120],"sparse":[19],"sum":[20],"of":[21,31,34,70,103,126],"kernels.":[23],"Each":[24],"kernel":[25],"bimodal":[28,71],"function":[29],"consisting":[30],"synchronous":[32],"snippets":[33],"an":[35,46],"audio":[36],"waveform":[37],"and":[38,55,59,129],"spatio-temporal":[40],"visual":[41,130],"basis":[42,77],"function.":[43],"To":[44],"represent":[45],"signal,":[48],"the":[49,94,106,115,124],"kernels":[50,72],"can":[51,97,117],"be":[52,98],"positioned":[53],"independently":[54],"arbitrarily":[56],"in":[57,105,110,123],"space":[58],"time.":[60],"proposed":[62],"algorithm":[63,116],"uses":[64],"unsupervised":[65],"learning":[66,82],"form":[68],"dictionaries":[69],"material.":[75],"functions":[78],"that":[79,93],"emerge":[80],"during":[81],"capture":[83],"salient":[84],"data":[86],"structures.":[87],"In":[88],"addition,":[89],"it":[90],"demonstrated":[92],"learned":[95],"dictionary":[96],"used":[99],"locate":[101],"sources":[102],"sound":[104],"movie":[107],"frame.":[108],"Specifically,":[109],"sequences":[111],"containing":[112],"two":[113],"speakers,":[114],"robustly":[118],"localize":[119],"speaker":[121],"even":[122],"presence":[125],"severe":[127],"acoustic":[128],"distracters.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":7}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
