{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:47:15Z","timestamp":1750308435473,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,29]],"date-time":"2019-10-29T00:00:00Z","timestamp":1572307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,29]]},"DOI":"10.1145\/3323503.3360299","type":"proceedings-article","created":{"date-parts":[[2019,10,10]],"date-time":"2019-10-10T13:04:27Z","timestamp":1570712667000},"page":"153-160","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Identification of speechless intervals in audio tracks using convolutional neural networks"],"prefix":"10.1145","author":[{"given":"Vin\u00edcius","family":"Wanderley","sequence":"first","affiliation":[{"name":"UFPB, Brazil, Jo\u00e3o Pessoa, Para\u00edba"}]},{"given":"Leonardo","family":"Villeth","sequence":"additional","affiliation":[{"name":"UFPB, Brazil, Jo\u00e3o Pessoa, Para\u00edba"}]},{"given":"Virg\u00ednia Pinto","family":"Campos","sequence":"additional","affiliation":[{"name":"UFPB, Brazil, Jo\u00e3o Pessoa, Para\u00edba"}]},{"given":"Tiago","family":"Maritan","sequence":"additional","affiliation":[{"name":"UFPB, Brazil, Jo\u00e3o Pessoa, Para\u00edba"}]},{"given":"Tha\u00eds","family":"Gaudencio","sequence":"additional","affiliation":[{"name":"UFPB, Brazil, Jo\u00e3o Pessoa, Para\u00edba"}]}],"member":"320","published-online":{"date-parts":[[2019,10,29]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n.d.]. American Council of The Blind.  [n.d.]. American Council of The Blind."},{"key":"e_1_3_2_1_2_1","unstructured":"[n.d.]. Youtube completa 10 anos com 300 horas de novos v\u00eddeos por minuto.  [n.d.]. Youtube completa 10 anos com 300 horas de novos v\u00eddeos por minuto."},{"key":"e_1_3_2_1_3_1","unstructured":"Soraya Ferreira Alves Veryanne Couto Teles and Tom\u00e1s Verdi Pereira. 2011. Propostas para um modelo brasileiro de audiodescri\u00e7\u00e3o para deficientes visuais. Tradu\u00e7\u00e3o Comunica\u00e7\u00e3o - Revista Brasileira de Tradutores 22 (2011) 9--29.  Soraya Ferreira Alves Veryanne Couto Teles and Tom\u00e1s Verdi Pereira. 2011. Propostas para um modelo brasileiro de audiodescri\u00e7\u00e3o para deficientes visuais. Tradu\u00e7\u00e3o Comunica\u00e7\u00e3o - Revista Brasileira de Tradutores 22 (2011) 9--29."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280624"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10209-018-0634-4"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461121.2461130"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44673-7_12"},{"volume-title":"Audio Set: An ontology and human-labeled dataset for audio events","year":"2017","author":"Gemmeke J.","key":"e_1_3_2_1_10_1"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0144610"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"S. Hershey S. Chaudhuri D. P. W. Ellis J. F. Gemmeke A. Jansen C. Moore M. Plakal D. Platt R. A. Saurous B. Seybold M. Slaney R. Weiss and K. Wilson. 2017. CNN Architectures for Large-Scale Audio Classification. In Intern. Confer. on Acoustics Speech and Signal Processing (ICASSP). https:\/\/arxiv.org\/abs\/1609.09430  S. Hershey S. Chaudhuri D. P. W. Ellis J. F. Gemmeke A. Jansen C. Moore M. Plakal D. Platt R. A. Saurous B. Seybold M. Slaney R. Weiss and K. Wilson. 2017. CNN Architectures for Large-Scale Audio Classification. In Intern. Confer. on Acoustics Speech and Signal Processing (ICASSP) . https:\/\/arxiv.org\/abs\/1609.09430","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"e_1_3_2_1_14_1","article-title":"Silence Removal from Audio Signal Using Framing and Windowing Method and Analyze Various","volume":"4","author":"Jasmine J. M.","year":"2016","journal-title":"Journal of Innovative Research in Computer and Communication Engineering"},{"key":"e_1_3_2_1_15_1","unstructured":"Qiuqiang Kong Yong Xu Wenwu Wang and Mark D. Plumbley. 2017. Audio Set classification with attention model: A probabilistic perspective. CoRR abs\/1711.00927 (2017). arXiv:1711.00927 http:\/\/arxiv.org\/abs\/1711.00927  Qiuqiang Kong Yong Xu Wenwu Wang and Mark D. Plumbley. 2017. Audio Set classification with attention model: A probabilistic perspective. CoRR abs\/1711.00927 (2017). arXiv:1711.00927 http:\/\/arxiv.org\/abs\/1711.00927"},{"key":"e_1_3_2_1_16_1","unstructured":"James Lakrit and Andrew Salway. 2002. The Semi-Automatic Generation of Audio Description from Screenplays. (2002).  James Lakrit and Andrew Salway. 2002. The Semi-Automatic Generation of Audio Description from Screenplays. (2002)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2019.8662396"},{"volume-title":"Shape, Contour and Grouping in Computer Vision","author":"LeCun Yann","key":"e_1_3_2_1_18_1"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.804546"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.3837\/tiis.2018.06.017"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472772"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2015.7324337"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-013-0479-5"},{"key":"e_1_3_2_1_24_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv 1409.1556 (09 2014).  Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv 1409.1556 (09 2014)."},{"key":"e_1_3_2_1_25_1","unstructured":"Agnieszka Szarkowska. 2011. Text-to-speech audio description: towards wider availability of AD. Journal of Specialised Translation 15 (01 2011) 142--163.  Agnieszka Szarkowska. 2011. Text-to-speech audio description: towards wider availability of AD. Journal of Specialised Translation 15 (01 2011) 142--163."},{"key":"e_1_3_2_1_26_1","unstructured":"N. Takahashi M. Gygli B. Pfister and L. Van Gool. 2016. Deep Convolutional Neural Networks and Data Augmentation for Acoustic Event Detection. CoRR abs\/1604.07160 (2016). arXiv:1604.07160 http:\/\/arxiv.org\/abs\/1604.07160  N. Takahashi M. Gygli B. Pfister and L. Van Gool. 2016. Deep Convolutional Neural Networks and Data Augmentation for Acoustic Event Detection. CoRR abs\/1604.07160 (2016). arXiv:1604.07160 http:\/\/arxiv.org\/abs\/1604.07160"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751969"},{"volume":"4","volume-title":"Speech and Signal Processing - ICASSP '07","author":"Temko A.","key":"e_1_3_2_1_28_1"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84882-054-8_7"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSSE.2017.8030927"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2229986"}],"event":{"name":"WebMedia '19: Brazilian Symposium on Multimedia and the Web","acronym":"WebMedia '19","location":"Rio de Janeiro Brazil"},"container-title":["Proceedings of the 25th Brazillian Symposium on Multimedia and the Web"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3323503.3360299","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3323503.3360299","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:49:54Z","timestamp":1750268994000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3323503.3360299"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,29]]},"references-count":31,"alternative-id":["10.1145\/3323503.3360299","10.1145\/3323503"],"URL":"https:\/\/doi.org\/10.1145\/3323503.3360299","relation":{},"subject":[],"published":{"date-parts":[[2019,10,29]]},"assertion":[{"value":"2019-10-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}