{"id":"https://openalex.org/W2979877392","doi":"https://doi.org/10.1145/3323503.3360299","title":"Identification of speechless intervals in audio tracks using convolutional neural networks","display_name":"Identification of speechless intervals in audio tracks using convolutional neural networks","publication_year":2019,"publication_date":"2019-10-10","ids":{"openalex":"https://openalex.org/W2979877392","doi":"https://doi.org/10.1145/3323503.3360299","mag":"2979877392"},"language":"en","primary_location":{"id":"doi:10.1145/3323503.3360299","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3323503.3360299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th Brazillian Symposium on Multimedia and the Web","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/A5012686795","display_name":"Vin\u00edcius Wanderley","orcid":null},"institutions":[{"id":"https://openalex.org/I169045520","display_name":"Universidade Federal da Para\u00edba","ror":"https://ror.org/00p9vpz11","country_code":"BR","type":"education","lineage":["https://openalex.org/I169045520"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Vin\u00edcius Wanderley","raw_affiliation_strings":["UFPB, Brazil, Jo\u00e3o Pessoa, Para\u00edba"],"affiliations":[{"raw_affiliation_string":"UFPB, Brazil, Jo\u00e3o Pessoa, Para\u00edba","institution_ids":["https://openalex.org/I169045520"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004415051","display_name":"Leonardo Villeth","orcid":null},"institutions":[{"id":"https://openalex.org/I169045520","display_name":"Universidade Federal da Para\u00edba","ror":"https://ror.org/00p9vpz11","country_code":"BR","type":"education","lineage":["https://openalex.org/I169045520"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Leonardo Villeth","raw_affiliation_strings":["UFPB, Brazil, Jo\u00e3o Pessoa, Para\u00edba"],"affiliations":[{"raw_affiliation_string":"UFPB, Brazil, Jo\u00e3o Pessoa, Para\u00edba","institution_ids":["https://openalex.org/I169045520"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083014360","display_name":"Virg\u00ednia Pinto Campos","orcid":"https://orcid.org/0000-0002-3874-1221"},"institutions":[{"id":"https://openalex.org/I169045520","display_name":"Universidade Federal da Para\u00edba","ror":"https://ror.org/00p9vpz11","country_code":"BR","type":"education","lineage":["https://openalex.org/I169045520"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Virg\u00ednia Pinto Campos","raw_affiliation_strings":["UFPB, Brazil, Jo\u00e3o Pessoa, Para\u00edba"],"affiliations":[{"raw_affiliation_string":"UFPB, Brazil, Jo\u00e3o Pessoa, Para\u00edba","institution_ids":["https://openalex.org/I169045520"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108764040","display_name":"Tiago Maritan","orcid":null},"institutions":[{"id":"https://openalex.org/I169045520","display_name":"Universidade Federal da Para\u00edba","ror":"https://ror.org/00p9vpz11","country_code":"BR","type":"education","lineage":["https://openalex.org/I169045520"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Tiago Maritan","raw_affiliation_strings":["UFPB, Brazil, Jo\u00e3o Pessoa, Para\u00edba"],"affiliations":[{"raw_affiliation_string":"UFPB, Brazil, Jo\u00e3o Pessoa, Para\u00edba","institution_ids":["https://openalex.org/I169045520"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049569354","display_name":"Tha\u00eds Gaud\u00eancio","orcid":null},"institutions":[{"id":"https://openalex.org/I169045520","display_name":"Universidade Federal da Para\u00edba","ror":"https://ror.org/00p9vpz11","country_code":"BR","type":"education","lineage":["https://openalex.org/I169045520"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Tha\u00eds Gaudencio","raw_affiliation_strings":["UFPB, Brazil, Jo\u00e3o Pessoa, Para\u00edba"],"affiliations":[{"raw_affiliation_string":"UFPB, Brazil, Jo\u00e3o Pessoa, Para\u00edba","institution_ids":["https://openalex.org/I169045520"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5012686795"],"corresponding_institution_ids":["https://openalex.org/I169045520"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20074803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"153","last_page":"160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9961000084877014,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9667999744415283,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8368138074874878},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7879910469055176},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.7227090001106262},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6866904497146606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5355491638183594},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48312804102897644},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.42956632375717163},{"id":"https://openalex.org/keywords/clothing","display_name":"Clothing","score":0.41729283332824707},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39872536063194275},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.355325847864151},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2199689745903015},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07940459251403809}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8368138074874878},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7879910469055176},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7227090001106262},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6866904497146606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5355491638183594},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48312804102897644},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.42956632375717163},{"id":"https://openalex.org/C530175646","wikidata":"https://www.wikidata.org/wiki/Q11460","display_name":"Clothing","level":2,"score":0.41729283332824707},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39872536063194275},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.355325847864151},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2199689745903015},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07940459251403809},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3323503.3360299","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3323503.3360299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th Brazillian Symposium on Multimedia and the Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4"},{"display_name":"Gender equality","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1535753778","https://openalex.org/W1547531277","https://openalex.org/W1622490909","https://openalex.org/W1650531274","https://openalex.org/W1675937194","https://openalex.org/W1686810756","https://openalex.org/W1972567154","https://openalex.org/W1985242443","https://openalex.org/W2109140708","https://openalex.org/W2131981197","https://openalex.org/W2136922672","https://openalex.org/W2161437536","https://openalex.org/W2192412620","https://openalex.org/W2194775991","https://openalex.org/W2342547278","https://openalex.org/W2398020690","https://openalex.org/W2526050071","https://openalex.org/W2570915410","https://openalex.org/W2593116425","https://openalex.org/W2754746744","https://openalex.org/W2765257474","https://openalex.org/W2811482466","https://openalex.org/W2888994383","https://openalex.org/W2922220370","https://openalex.org/W4231109964"],"related_works":["https://openalex.org/W2738456166","https://openalex.org/W2352745894","https://openalex.org/W2057731951","https://openalex.org/W2358836583","https://openalex.org/W2064629212","https://openalex.org/W2387983088","https://openalex.org/W2135888309","https://openalex.org/W3080469217","https://openalex.org/W791876968","https://openalex.org/W2768638338"],"abstract_inverted_index":{"Audio":[0],"description":[1,159],"(AD)":[2],"is":[3,45,59,92,127],"an":[4,43,154],"accessibility":[5],"resource":[6],"designed":[7],"to":[8,61,93,101,128,150,189],"improve":[9],"access":[10],"for":[11,111,143,173],"blind":[12],"or":[13,156],"low":[14],"vision":[15],"individuals":[16],"by":[17],"describing":[18],"images,":[19],"narrating":[20],"actions":[21],"and":[22,140],"visual":[23],"elements,":[24],"such":[25],"as":[26],"scene":[27],"details,":[28],"some":[29],"aspects":[30],"of":[31,50,83,114,171,176,187],"the":[32,51,66,69,74,84,88,95,133,138,174,177,180,195],"character":[33],"(eg,":[34],"age,":[35],"gender,":[36],"clothing),":[37],"among":[38],"others.":[39],"However,":[40],"in":[41,48,68,87,117,132],"general,":[42],"AD":[44,89,134],"only":[46],"generated":[47],"sections":[49],"video":[52],"that":[53],"do":[54],"not":[55],"contain":[56],"dialogue.":[57],"This":[58],"done":[60],"prevent":[62],"any":[63],"overlap":[64],"with":[65],"dialogue":[67],"video,":[70],"which":[71,98],"may":[72],"hinder":[73],"user's":[75],"understanding":[76],"rather":[77],"than":[78],"helping":[79],"it.":[80],"Thus,":[81],"one":[82],"first":[85],"steps":[86],"generation":[90,135,160],"process":[91],"identify":[94,190],"speechless":[96,115,191],"intervals,":[97],"are":[99],"candidates":[100],"receive":[102],"AD.":[103,145],"In":[104],"this":[105,130],"work,":[106],"we":[107],"present":[108],"a":[109,167,183],"solution":[110,181],"automatic":[112,155],"identification":[113],"intervals":[116],"digital":[118],"videos":[119,196],"using":[120],"Convolutional":[121],"Neural":[122],"Networks":[123],"(CNNs).":[124],"Our":[125],"proposal":[126],"automate":[129],"step":[131],"process,":[136],"reducing":[137],"time":[139],"effort":[141],"involved":[142],"generating":[144],"Another":[146],"alternative":[147],"would":[148],"be":[149],"integrate":[151],"it":[152],"into":[153],"semi-automatic":[157],"audio":[158],"system.":[161],"The":[162],"results":[163],"shows":[164],"that,":[165],"considering":[166,193],"minimum":[168],"confidence":[169],"level":[170],"0.5":[172],"output":[175],"classification":[178],"model,":[179],"obtained":[182],"balanced":[184],"average":[185],"accuracy":[186],"93%":[188],"segments":[192],"all":[194],"tested.":[197]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}