{"id":"https://openalex.org/W147552647","doi":"https://doi.org/10.21437/interspeech.2009-337","title":"Robust audio-based classification of video genre","display_name":"Robust audio-based classification of video genre","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W147552647","doi":"https://doi.org/10.21437/interspeech.2009-337","mag":"147552647"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-337","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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/A5071001941","display_name":"Micka\u00ebl Rouvier","orcid":"https://orcid.org/0000-0003-3541-3385"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mickael Rouvier","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050508708","display_name":"Georges Linar\u00e8s","orcid":"https://orcid.org/0000-0001-8049-9056"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georges Linar\u00e8s","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5017334281","display_name":"Driss Matrouf","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Driss Matrouf","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5071001941"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4284,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79655172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1159","last_page":"1162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9939000010490417,"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/T11309","display_name":"Music and Audio Processing","score":0.9939000010490417,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9217000007629395,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9150999784469604,"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/computer-science","display_name":"Computer science","score":0.7547056674957275},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46315398812294006},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.44919678568840027},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.39029747247695923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3653952181339264},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2559303641319275},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2353796362876892}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7547056674957275},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46315398812294006},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.44919678568840027},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.39029747247695923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3653952181339264},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2559303641319275},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2353796362876892}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2009-337","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.333.1360","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.333.1360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://lia.univ-avignon.fr/fileadmin/documents/Users/Intranet/chercheurs/linares/Publis/Mickael_INTER09_RVGI.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-01320224v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01320224","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":"INTERSPEECH, Sep 2009, Brighton, United Kingdom","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W106647055","https://openalex.org/W1563750459","https://openalex.org/W1863069154","https://openalex.org/W2100454127","https://openalex.org/W2109788830","https://openalex.org/W2111339787","https://openalex.org/W2113144451","https://openalex.org/W2121750345","https://openalex.org/W2142526407","https://openalex.org/W2151920764","https://openalex.org/W2156861313","https://openalex.org/W2904424563"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880"],"abstract_inverted_index":{"Video":[0],"genre":[1,28,66,104],"classification":[2],"is":[3,68],"a":[4,8,23,75,82],"challenging":[5],"task":[6],"in":[7],"global":[9],"context":[10],"of":[11,39,51,99],"fast":[12],"growing":[13],"video":[14,27,103,107],"collections":[15],"available":[16],"on":[17,36,70,81,92],"the":[18,37,48],"Internet.":[19],"This":[20],"paper":[21],"presents":[22],"new":[24],"method":[25],"for":[26],"identification":[29,67,97],"by":[30,73],"audio":[31,44],"analysis.":[32],"Our":[33],"approach":[34],"relies":[35],"combination":[38],"low":[40],"and":[41,61,90],"high":[42],"level":[43],"features.":[45],"We":[46],"investigate":[47],"discriminative":[49],"capacity":[50],"features":[52,72],"related":[53],"to":[54],"acoustic":[55,62],"instability,":[56],"speaker":[57],"interactivity,":[58],"speech":[59],"quality":[60],"space":[63],"characterization.":[64],"The":[65],"performed":[69],"these":[71],"using":[74],"SVM":[76],"classifier.":[77],"Experiments":[78],"are":[79],"conducted":[80],"corpus":[83],"composed":[84],"from":[85],"cartoons,":[86],"movies,":[87],"news,":[88],"commercials":[89],"musics":[91],"which":[93],"we":[94],"obtain":[95],"an":[96],"rate":[98],"91%.":[100],"Index":[101],"Terms:":[102],"classification,":[105],"audio-based":[106],"processing":[108]},"counts_by_year":[{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}