{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T03:34:50Z","timestamp":1769052890523,"version":"3.49.0"},"reference-count":94,"publisher":"Springer Science and Business Media LLC","issue":"25","license":[{"start":{"date-parts":[[2021,8,30]],"date-time":"2021-08-30T00:00:00Z","timestamp":1630281600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,8,30]],"date-time":"2021-08-30T00:00:00Z","timestamp":1630281600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100004612","name":"Fundacao Araucaria","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004612","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/fund","name":"Universidade Estadual do Oeste do Parana","doi-asserted-by":"publisher","id":[{"id":"10.13039\/fund","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Coordenacao de Aperfeicoamento de Pessoal de Nivel Superior","award":["001"],"award-info":[{"award-number":["001"]}]},{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cientco e Tecnologico","doi-asserted-by":"publisher","award":["142050\/2019-9"],"award-info":[{"award-number":["142050\/2019-9"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1007\/s11042-021-11401-1","type":"journal-article","created":{"date-parts":[[2021,8,30]],"date-time":"2021-08-30T01:03:20Z","timestamp":1630285400000},"page":"33971-34017","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["A video indexing and retrieval computational prototype based on transcribed speech"],"prefix":"10.1007","volume":"80","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0748-3693","authenticated-orcid":false,"given":"Newton","family":"Spola\u00f4r","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huei Diana","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weber Shoity Resende","family":"Takaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leandro Augusto","family":"Ensina","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio Rafael Sabino","family":"Parmezan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jefferson Tales","family":"Oliva","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claudio Saddy Rodrigues","family":"Coy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng Chung","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,30]]},"reference":[{"key":"11401_CR1","doi-asserted-by":"publisher","unstructured":"Agharwal A, Kovvuri R, Nevatia R, Snoek CGM (2016) Tag-based video retrieval by embedding semantic content in a continuous word space. In IEEE Winter Conf Appl Comput Vis New York. IEEE, The United States of America, pp 1\u20138.\u00a0https:\/\/doi.org\/10.1109\/WACV.2016.7477706","DOI":"10.1109\/WACV.2016.7477706"},{"key":"11401_CR2","doi-asserted-by":"publisher","unstructured":"Akosu N, Selamat A (2014) Enhancing the effectiveness of the spelling checker approach for language identification. In: Badica A, Trawinski B, Nguyen NT (eds) Recent Developments in Computational Collective Intelligence, Studies in Computational Intelligence, vol 513, Springer International Publishing, Cham, pp 157\u201316.\u00a0https:\/\/doi.org\/10.1007\/978-3-31901787-7_15","DOI":"10.1007\/978-3-31901787-7_15"},{"key":"11401_CR3","doi-asserted-by":"publisher","unstructured":"Al Kabary I, Schuldt H (2014) Enhancing sketch-based sport video retrieval by suggesting relevant motion paths. In: ACM SIGIR Conference on Research and Development in Information Retrieval, ACM, New\u00a0York, The United States of America, pp 1227\u20131230. https:\/\/doi.org\/10.1145\/2600428.2609551","DOI":"10.1145\/2600428.2609551"},{"key":"11401_CR4","doi-asserted-by":"publisher","unstructured":"Ambekar T, Musande V (2017) A novel approach to personalize the health care video search. In: International Conference on Intelligent Systems and Information Management, IEEE, New York, The United States of America, pp 212\u2013216, https:\/\/doi.org\/10.1109\/ICISIM.2017.8122175","DOI":"10.1109\/ICISIM.2017.8122175"},{"issue":"2","key":"11401_CR5","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1155\/S111086570321012X","volume":"2003","author":"A Amir","year":"2003","unstructured":"Amir A, Srinivasan S, Efrat A (2003) Search the audio, browse the video\u2013a generic paradigm for video collections. EURASIP J Adv Sig Pr 2003(2):209\u2013222. https:\/\/doi.org\/10.1155\/S111086570321012X","journal-title":"EURASIP J Adv Sig Pr"},{"key":"11401_CR6","unstructured":"Amorim MN, Segundo RMC, Santos CAS, Tavares OL (2017) Crowdnote: Crowdsourcing environment for complex video annotations. In: Brazilian Symposium of Multimedia Systems and the Web\u2013Tools and Applications Workshop, Brazilian Computer Society, Porto Alegre, Brazil, pp 194\u2013198"},{"issue":"2","key":"11401_CR7","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1016\/j.jfds.2018.02.002","volume":"4","author":"A Atkins","year":"2018","unstructured":"Atkins A, Niranjan M, Gerding E (2018) Financial news predicts stock market volatility better than close price. J Finance Data Sci 4(2):120\u2013137. https:\/\/doi.org\/10.1016\/j.jfds.2018.02.002","journal-title":"J Finance Data Sci"},{"key":"11401_CR8","doi-asserted-by":"publisher","unstructured":"Barra GDO, Lux M, I-Nieto XG (2016) Large scale content-based video retrieval with LIvRE. In: International Workshop on Content-Based Multimedia Indexing, IEEE, New York, The United States of America, pp 1\u20134. https:\/\/doi.org\/10.1109\/CBMI.2016.7500266","DOI":"10.1109\/CBMI.2016.7500266"},{"issue":"5\u20137","key":"11401_CR9","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1177\/0278364917691112","volume":"36","author":"E Bastianelli","year":"2017","unstructured":"Bastianelli E, Castellucci G, Croce D, Basili R, Nardi D (2017) Structured learning for spoken language understanding in human-robot interaction. Int J Robot Res 36(5\u20137):660\u2013683. https:\/\/doi.org\/10.1177\/0278364917691112","journal-title":"Int J Robot Res"},{"key":"11401_CR10","doi-asserted-by":"publisher","unstructured":"Bernard G, Lebboss G (2017) Methods for word encoding: A survey. In: International Conference on Engineering and Technology, IEEE, New York, The United States of America, pp 1\u20136. https:\/\/doi.org\/10.1109\/ICEngTechnol.2017.8308139","DOI":"10.1109\/ICEngTechnol.2017.8308139"},{"key":"11401_CR11","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.specom.2013.07.008","volume":"56","author":"L Besacier","year":"2014","unstructured":"Besacier L, Barnard E, Karpov A, Schultz T (2014) Automatic speech recognition for under-resourced languages: A survey. Speech Commun 56:85\u2013100. https:\/\/doi.org\/10.1016\/j.specom.2013.07.008","journal-title":"Speech Commun"},{"key":"11401_CR12","volume-title":"Natural Language Processing with Python - Analyzing Text with the Natural Language Toolkit","author":"S Bird","year":"2009","unstructured":"Bird S, Klein E, Loper E (2009) Natural Language Processing with Python - Analyzing Text with the Natural Language Toolkit. O\u2019Reilly Media, Sebastopol, The United States of America"},{"key":"11401_CR13","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1016\/j.neucom.2016.09.140","volume":"265","author":"DA Bonilla Cardona","year":"2017","unstructured":"Bonilla Cardona DA, Nedjah N, Mourelle LM (2017) Online phoneme recognition using multi-layer perceptron networks combined with recurrent non-linear autoregressive neural networks with exogenous inputs. Neurocomputing 265:78\u201390","journal-title":"Neurocomputing"},{"key":"11401_CR14","doi-asserted-by":"publisher","unstructured":"Cao Y, Tavanapong W, Li D, Oh J, de Groen PC, Wong J (2004) A visual model approach for parsing colonoscopy videos. In: Enser P, Kompatsiaris Y, O\u2019Connor NE, Smeaton AF, Smeulders AWM (eds) Image and Video Retrieval, Lecture Notes in Computer Science, vol 3115, Springer Berlin Heidelberg, Berlin, Germany, pp 160\u2013169. https:\/\/doi.org\/10.1007\/978-3-540-27814-6_22","DOI":"10.1007\/978-3-540-27814-6_22"},{"key":"11401_CR15","doi-asserted-by":"publisher","unstructured":"Carpineto C, Romano G (2012) A survey of automatic query expansion in information retrieval. ACM Comput Surv 44(1):1:1\u20131:50. https:\/\/doi.org\/10.1145\/2071389.2071390","DOI":"10.1145\/2071389.2071390"},{"key":"11401_CR16","doi-asserted-by":"publisher","unstructured":"Charri\u00e9re K, Quellec G, Lamard M, Coatrieux G, Cochener B, Cazuguel G (2014) Automated surgical step recognition in normalized cataract surgery videos. In: Int Conf IEEE Eng Med Biol Soc, IEEE, New York, The United States of America, pp 4647\u20134650. https:\/\/doi.org\/10.1109\/EMBC.2014.6944660","DOI":"10.1109\/EMBC.2014.6944660"},{"issue":"6","key":"11401_CR17","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1016\/j.cviu.2013.02.003","volume":"117","author":"J Choi","year":"2013","unstructured":"Choi J, Wang Z, Lee S, Jeon WJ (2013) A spatio-temporal pyramid matching for video retrieval. Comput Vis Image Und 117(6):660\u2013669. https:\/\/doi.org\/10.1016\/j.cviu.2013.02.003","journal-title":"Comput Vis Image Und"},{"key":"11401_CR18","doi-asserted-by":"publisher","unstructured":"Christel MG, Huang C, Moraveji N, Papernick N (2004) Exploiting multiple modalities for interactive video retrieval. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE, New York, The United States of America, vol 3, pp 1032\u20131035. https:\/\/doi.org\/10.1109\/ICASSP.2004.1326724","DOI":"10.1109\/ICASSP.2004.1326724"},{"key":"11401_CR19","volume-title":"Distributed systems: concepts and design","author":"G Coulouris","year":"2011","unstructured":"Coulouris G, Dollimore J, Kindberg T, Blair G (2011) Distributed systems: concepts and design. Addison-Wesley, Boston, The United States of America"},{"key":"11401_CR20","doi-asserted-by":"publisher","unstructured":"D\u2019agostino RB, Belanger A, Jr RBD (1990) A suggestion for using powerful and informative tests of normality. Am Stat 44(4):316\u2013321. https:\/\/doi.org\/10.1080\/00031305.1990.10475751","DOI":"10.1080\/00031305.1990.10475751"},{"key":"11401_CR21","doi-asserted-by":"publisher","unstructured":"Das D, Chen D, Hauptmann AG (2008) Improving multimedia retrieval with a video ocr. In: Gevers T, Jain RC, Santini S (eds) Multimedia Content Access: Algorithms and Systems II, Proceedings of SPIE, vol 6820, SPIE, Bellingham, The United States of America, pp 68200B\u20131\u2013 68200B\u201312. https:\/\/doi.org\/10.1117\/12.766931","DOI":"10.1117\/12.766931"},{"key":"11401_CR22","doi-asserted-by":"publisher","unstructured":"de Toledo TF, Lee HD, Spola\u00f4r N, Coy CSR, Wu FC (2019) Web system prototype based on speech recognition to construct medical reports in Brazilian Portuguese. Int J M\u00e9d Informatics 121:39\u201352.\u00a0https:\/\/doi.org\/10.1016\/j.ijmedinf.2018.10.010","DOI":"10.1016\/j.ijmedinf.2018.10.010"},{"issue":"4","key":"11401_CR23","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1145\/1924421.1924442","volume":"54","author":"A Doan","year":"2011","unstructured":"Doan A, Ramakrishnan R, Halevy AY (2011) Crowdsourcing systems on the world-wide web. Commun ACM 54(4):86\u201396. https:\/\/doi.org\/10.1145\/1924421.1924442","journal-title":"Commun ACM"},{"issue":"3","key":"11401_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4018\/IJIIT.2018.070101","volume":"14","author":"A Ghoulam","year":"2018","unstructured":"Ghoulam A, Barigou F, Belalem G, Meziane F (2018) Query expansion using medical information extraction for improving information retrieval in french medical domain. Int J Intell Inf Technol 14(3):1\u201317. https:\/\/doi.org\/10.4018\/IJIIT.2018.070101","journal-title":"Int J Intell Inf Technol"},{"key":"11401_CR25","doi-asserted-by":"crossref","unstructured":"Giannakopoulos T, Pikrakis A, Theodoridis S (2008) A novel efficient approach for audio segmentation. In: Int Conf Pattern Recognit, IEEE, Tampa, The United States of America, pp 1\u20134","DOI":"10.1109\/ICPR.2008.4761654"},{"key":"11401_CR26","unstructured":"Girish KVV (2019) Beginner\u2019s guide to speech analysis. https:\/\/towardsdatascience.com\/beginners-guide-to-speech-analysis4690ca7a7c05"},{"key":"11401_CR27","doi-asserted-by":"publisher","unstructured":"Goel P, Giangreco I, Rossetto L, T\u0103nase C, Schuldt H(2017) \u201chey,vitrivr!\u201d \u2013 a multimodal ui for video retrieval. In: Jose JM, Hauff C, Alt\u0131ngovde IS, Song D, Albakour D, Watt S, Tait J (eds) Advances in Information Retrieval, Springer International Publishing, Cham, Switzerland, pp 749\u2013752. https:\/\/doi.org\/10.1007\/978-3-319-56608-5_7","DOI":"10.1007\/978-3-319-56608-5_7"},{"key":"11401_CR28","unstructured":"G\u00f3mez-Dur\u00e1n J, Simancas-Garc\u00eda J, Acosta-Coll M, Mel\u00e9ndez-Pertuz F, V\u00e9lez-Zapata J (2017) Speech recognition algorithm based on nonlinear techniques (in spanish). Espacios 38(17):4\u201321.\u00a0https:\/\/repositorio.cuc.edu.co\/xmlui\/handle\/11323\/904"},{"key":"11401_CR29","doi-asserted-by":"publisher","unstructured":"Granell E, Romero V, Mart\u00ednezHinarejos CD (2018) Multimodality, interactivity, and crowdsourcing for document transcription. Comput Intell 34(2):398\u2013419. https:\/\/doi.org\/10.1111\/coin.12169","DOI":"10.1111\/coin.12169"},{"key":"11401_CR30","doi-asserted-by":"publisher","unstructured":"Hu W, Xie N, Li L, Zeng X, Maybank S (2011) A survey on visual content based video indexing and retrieval. IEEE Trans Syst Man Cyber C Appl Rev 41(6):797\u2013819. https:\/\/doi.org\/10.1109\/TSMCC.2011.2109710","DOI":"10.1109\/TSMCC.2011.2109710"},{"issue":"4","key":"11401_CR31","doi-asserted-by":"publisher","first-page":"1166","DOI":"10.1109\/TMM.2012.2193561","volume":"14","author":"B Huurnink","year":"2012","unstructured":"Huurnink B, Snoek CGM, de Rijke M, Smeulders AWM (2012) Content-based analysis improves audiovisual archive retrieval. IEEE Trans Multimedia 14(4):1166\u20131178. https:\/\/doi.org\/10.1109\/TMM.2012.2193561","journal-title":"IEEE Trans Multimedia"},{"key":"11401_CR32","doi-asserted-by":"publisher","unstructured":"Ianeva TI, Vries APD, Westerveld T (2004) A dynamic probabilistic multimedia retrieval model. In: IEEE International Conference on Multimedia and Expo, IEEE, New York, The United States of America, vol 3, pp 1607\u20131610. https:\/\/doi.org\/10.1109\/ICME.2004.1394557","DOI":"10.1109\/ICME.2004.1394557"},{"issue":"3","key":"11401_CR33","doi-asserted-by":"publisher","first-page":"209","DOI":"10.3169\/mta.4.209","volume":"4","author":"N Inoue","year":"2016","unstructured":"Inoue N, Shinoda K (2016) Semantic indexing for large-scale video retrieval. ITE Trans Media Technol Appl 4(3):209\u2013217. https:\/\/doi.org\/10.3169\/mta.4.209","journal-title":"ITE Trans Media Technol Appl"},{"key":"11401_CR34","doi-asserted-by":"publisher","unstructured":"Iwata S, Ohyama W, Wakabayashi T, Kimura F (2016) Recognition and transition frame detection of arabic news captions for video retrieval. In: Int Conf Pattern Recognit, IEEE, New York, The United States of America, pp 4005\u20134010. https:\/\/doi.org\/10.1109\/ICPR.2016.7900260","DOI":"10.1109\/ICPR.2016.7900260"},{"key":"11401_CR35","doi-asserted-by":"publisher","unstructured":"Ji X, Han J, Hu X, Li K, Deng F, Fang J, Guo L, Liu T (2011) Retrieving video shots in semantic brain imaging space using manifold-ranking. In: IEEE International Conference on Image Processing, IEEE, New York, The United States of America, pp 3633\u20133636. https:\/\/doi.org\/10.1109\/ICIP.2011.6116505","DOI":"10.1109\/ICIP.2011.6116505"},{"key":"11401_CR36","doi-asserted-by":"publisher","unstructured":"Jiang L, Yu S, Meng D, Yang Y, Mitamura T, Hauptmann AG (2015) Fast and accurate content-based semantic search in 100m internet videos. In: ACM International Conference on Multimedia, ACM, New York, The United States of America, pp 49\u201358. https:\/\/doi.org\/10.1145\/2733373.2806237","DOI":"10.1145\/2733373.2806237"},{"issue":"1","key":"11401_CR37","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1186\/14726947-14-94","volume":"14","author":"M Johnson","year":"2014","unstructured":"Johnson M, Lapkin S, Long V, Sanchez P, Suominen H, Basilakis J, Dawson L (2014) A systematic review of speech recognition technology in health care. BMC Med Inform Decis Mak 14(1):94. https:\/\/doi.org\/10.1186\/14726947-14-94","journal-title":"BMC Med Inform Decis Mak"},{"key":"11401_CR38","unstructured":"Johnston AB, Burnett DC (2001) Professional Java Server Programming J2EE 1.3 Edition. Wrox Press, Birmingham, United Kingdom\u00a0"},{"key":"11401_CR39","volume-title":"WebRTC: APIs and RTCWEB Protocols of the HTML5 Real-Time Web","author":"AB Johnston","year":"2014","unstructured":"Johnston AB, Burnett DC (2014) WebRTC: APIs and RTCWEB Protocols of the HTML5 Real-Time Web, 3rd edn. Digital Codex LLC, Saint Louis, The United States of America","edition":"3"},{"key":"11401_CR40","doi-asserted-by":"publisher","unstructured":"Kamabathula VK, Iyer S (2011) Automated tagging to enable fine-grained browsing of lecture videos. In: 2011 IEEE International Conference on\u00a0Technology for Education, IEEE, New York, The United States of America, pp 96\u2013102. https:\/\/doi.org\/10.1109\/T4E.2011.23","DOI":"10.1109\/T4E.2011.23"},{"issue":"2","key":"11401_CR41","first-page":"16","volume":"13","author":"A Kayama","year":"2007","unstructured":"Kayama A, Carvalho F, Castro L, Herr M, Rubim M, P\u00e1dua M, Mattos W (2007) Sung Brazilian Portuguese: Pronunciation standards for Brazilian Portuguese in scholarly chant (in Portuguese). OPUS 13(2):16\u201338. https:\/\/www.anppom.com.br\/revista\/index.php\/opus\/article\/view\/300","journal-title":"OPUS"},{"issue":"3\u20134","key":"11401_CR42","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1023\/A:1011348306007","volume":"4","author":"T Kemp","year":"2001","unstructured":"Kemp T, Weber M, Waibel A (2001) The ISL view4you broadcast news transcription system. Int J Speech Technol 4(3\u20134):177\u2013191. https:\/\/doi.org\/10.1023\/A:1011348306007","journal-title":"Int J Speech Technol"},{"key":"11401_CR43","doi-asserted-by":"publisher","unstructured":"Larson M, Newman E, Jones GJF (2010) Overview of videoclef 2009: New perspectives on speech-based multimedia content enrichment. In: Peters C, Caputo B, Gonzalo J, Jones GJF, Kalpathy-Cramer J, M\u00fcller H, Tsikrika T (eds) Multilingual Information Access Evaluation II. Multimedia Experiments, Lecture Notes in Computer Science, vol 6242, Springer-Verlag, Berlin, Germany, pp 354\u2013368. https:\/\/doi.org\/10.1007\/978-3-642-15751-6_46","DOI":"10.1007\/978-3-642-15751-6_46"},{"key":"11401_CR44","unstructured":"Li H, Bao L, Gao Z, Overwijk A, Liu W, Zhang L, Yu S, Chen M, Metze F, Hauptmann AG (2010) Informedia @ trecvid 2010. https:\/\/www.cs.unc.edu\/~wliu\/papers\/trecvid2010_informedia.pdf"},{"issue":"2","key":"11401_CR45","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1147\/rd.22.0159","volume":"2","author":"HP Luhn","year":"1958","unstructured":"Luhn HP (1958) The automatic creation of literature abstracts. IBM J Res Dev 2(2):159\u2013165. https:\/\/doi.org\/10.1147\/rd.22.0159","journal-title":"IBM J Res Dev"},{"key":"11401_CR46","doi-asserted-by":"publisher","unstructured":"Luong TH, Pham NM, Vu QH (2016) Vietnamese multimedia agricultural information retrieval system as an info service. In: Murakami Y, Lin D (eds) International Workshop on Worldwide Language Service Infrastructure, Lecture Notes in Computer Science, vol 9442, Springer International Publishing, Cham, Switzerland, pp 147\u2013160. https:\/\/doi.org\/10.1007\/978-3319-31468-6_11","DOI":"10.1007\/978-3319-31468-6_11"},{"issue":"1","key":"11401_CR47","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1590\/S2237-93632012000100007","volume":"32","author":"RB Machado","year":"2012","unstructured":"Machado RB, Lee HD, Ayrizono MDLS, Leal RF, Coy CSR, Fagundes JJ, Wu FC (2012) Prototype of a computer system for managing data and video colonoscopy exams. J Coloproctol (Rio de Janeiro) 32(1):50\u201359. https:\/\/doi.org\/10.1590\/S2237-93632012000100007","journal-title":"J Coloproctol (Rio de Janeiro)"},{"key":"11401_CR48","unstructured":"Mitrovi\u0107 D, Zeppelzauer M, Zaharieva M, Breiteneder C (2011) Retrieval of visual composition in film. In:\u00a0 International Workshop on Image Analysis for Multimedia Interactive Services, TU Delft, Delft, The Netherlands, pp 1\u20134"},{"key":"11401_CR49","doi-asserted-by":"publisher","unstructured":"M\u00fchling M, Meister M, Korfhage N, Wehling J, H\u00f6rth A, Ewerth R, Freisleben B (2016) Content-based video retrieval in historical collections of the german broadcasting archive. In: Fuhr N, Kov\u00e1cs L, Risse T, Nejdl W (eds) International Conference on Theory and Practice of Digital Libraries, Lecture Notes in Computer Science, vol 9819, Springer International Publishing, Cham, Switzerland, pp 67\u201378. https:\/\/doi.org\/10.1007\/978-3-31943997-6_6","DOI":"10.1007\/978-3-31943997-6_6"},{"issue":"1","key":"11401_CR50","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/s13173-010-0023-1","volume":"17","author":"N Neto","year":"2011","unstructured":"Neto N, Patrick C, Klautau A, Trancoso I (2011) Free tools and resources for Brazilian Portuguese speech recognition. J Braz Comput Soc 17(1):53\u201368. https:\/\/doi.org\/10.1007\/s13173-010-0023-1","journal-title":"J Braz Comput Soc"},{"key":"11401_CR51","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.eswa.2018.08.004","volume":"115","author":"JT Oliva","year":"2019","unstructured":"Oliva JT, Lee HD, Spola\u00f4r N, Takaki WSR, Coy CSR, Fagundes JJ, Wu FC (2019) A computational system based on ontologies to automate the mapping process of medical reports into structured databases. Expert Syst Appl 115:37\u201356. https:\/\/doi.org\/10.1016\/j.eswa.2018.08.004","journal-title":"Expert Syst Appl"},{"key":"11401_CR52","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1007\/s10772-019-09598-6","volume":"22","author":"M Pala","year":"2019","unstructured":"Pala M, Parayitam L, Appala V (2019) Real-time transcription, keyword spotting, archival and retrieval for telugu tv news using ASR. Int J Speech Technol 22:433\u2013439. https:\/\/doi.org\/10.1007\/s10772-019-09598-6","journal-title":"Int J Speech Technol"},{"issue":"23","key":"11401_CR53","doi-asserted-by":"publisher","first-page":"10923","DOI":"10.1007\/s11042-014-2311-9","volume":"74","author":"MHR Pereira","year":"2015","unstructured":"Pereira MHR, de Souza CL, P\u00e1dua FLC, Silva GD, de Assis GT, Pereira ACM (2015) SAPTE: A multimedia information system to support the discourse analysis and information retrieval of television programs. Multimed Tools Appl 74(23):10923\u201310963. https:\/\/doi.org\/10.1007\/s11042-014-2311-9","journal-title":"Multimed Tools Appl"},{"key":"11401_CR54","doi-asserted-by":"publisher","unstructured":"Pham NM, Vu QH (2013) Acoustic modeling for under-resourced languages: A role in Vietnamese soccer video retrieval. In: International Conference on Advanced Technologies for Communications, IEEE, New York, The United States of America, pp 652\u2013656. https:\/\/doi.org\/10.1109\/ATC.2013.6698195","DOI":"10.1109\/ATC.2013.6698195"},{"key":"11401_CR55","doi-asserted-by":"publisher","unstructured":"Pham NM, Vu QH (2013) Temporal confusion network for speech-based soccer event retrieval. In: International Conference on Advanced Technologies for Communications, IEEE, New York, The United States of America, pp 549\u2013553. https:\/\/doi.org\/10.1109\/ATC.2013.6698176","DOI":"10.1109\/ATC.2013.6698176"},{"key":"11401_CR56","doi-asserted-by":"publisher","unstructured":"Pranali B, Anil W, Kokhale S (2015) Inhalt based video recuperation system using OCR and ASR technologies. In: International Conference on Computational Intelligence and Communication Networks, IEEE, New York, The United States of America, pp 382\u2013386. https:\/\/doi.org\/10.1109\/CICN.2015.315","DOI":"10.1109\/CICN.2015.315"},{"key":"11401_CR57","volume-title":"Software Engineering: A Practitioner\u2019s Approach","author":"RS Pressman","year":"2010","unstructured":"Pressman RS (2010) Software Engineering: A Practitioner\u2019s Approach, 7th edn. McGraw-Hill, Boston, The United States of America","edition":"7"},{"issue":"5","key":"11401_CR58","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1007\/s11704-013-1276-6","volume":"7","author":"R Priya","year":"2013","unstructured":"Priya R, Shanmugam TN (2013) A comprehensive review of significant researches on content based indexing and retrieval of visual information. Front Comput Sci 7(5):782\u2013799. https:\/\/doi.org\/10.1007\/s11704-013-1276-6","journal-title":"Front Comput Sci"},{"key":"11401_CR59","volume-title":"Colonoscopy (in Portuguese)","author":"AF Quilici","year":"2000","unstructured":"Quilici AF (2000) Colonoscopy (in Portuguese). Lemos, S\u00e3o Paulo, Brazil"},{"key":"11401_CR60","doi-asserted-by":"publisher","unstructured":"Radha N (2016) Video retrieval using speech and text in video. In: International Conference on Inventive Computation Technologies, IEEE, New York, The United States of America, pp 1\u20136. https:\/\/doi.org\/10.1109\/INVENTIVE.2016.7824801","DOI":"10.1109\/INVENTIVE.2016.7824801"},{"issue":"11","key":"11401_CR61","doi-asserted-by":"publisher","first-page":"131","DOI":"10.14569\/IJACSA.2012.031121","volume":"3","author":"MM Rahman","year":"2012","unstructured":"Rahman MM, Bhuiyan MA (2012) Continuous bangla speech segmentation using short-term speech features extraction approaches. Int J Adv Comput Sci Appl 3(11):131\u2013138. https:\/\/doi.org\/10.14569\/IJACSA.2012.031121","journal-title":"Int J Adv Comput Sci Appl"},{"key":"11401_CR62","doi-asserted-by":"publisher","unstructured":"Rautiainen M, Ojala T, Sepp\u00e4nen T (2004) Analysing the performance of visual, concept and text features in content-based video retrieval. In: ACM SIGMM International Workshop on Multimedia Information Retrieval, ACM, New York, The United States of America, pp 197\u2013204. https:\/\/doi.org\/10.1145\/1026711.1026744","DOI":"10.1145\/1026711.1026744"},{"issue":"6","key":"11401_CR63","first-page":"2156","volume":"7","author":"M Ravinder","year":"2016","unstructured":"Ravinder M, Venugopal T (2016) Content-based video indexing and retrieval using block based local binary patterns and pixel change ratio map (bblbppcrm). Int J Eng Technol 7(6):2156\u20132162. http:\/\/www.enggjournals.com\/ijet\/docs\/IJET15-07-06-050.pdf","journal-title":"Int J Eng Technol"},{"issue":"3","key":"11401_CR64","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1145\/1597849.1384278","volume":"40","author":"S Repp","year":"2008","unstructured":"Repp S, Linckels S, Meinel C (2008) Question answering from lecture videos based on an automatic semantic annotation. SIGCSE Bull 40(3):17\u201321. https:\/\/doi.org\/10.1145\/1597849.1384278","journal-title":"SIGCSE Bull"},{"key":"11401_CR65","doi-asserted-by":"publisher","unstructured":"Rooij OD, Worring M (2012) Efficient targeted search using a focus and context video browser. ACM Trans Multimedia Comput Commun Appl 8(4):51:1\u201351:19. https:\/\/doi.org\/10.1145\/2379790.2379793","DOI":"10.1145\/2379790.2379793"},{"issue":"3","key":"11401_CR66","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1109\/MIS.2013.9","volume":"28","author":"VP Rosas","year":"2013","unstructured":"Rosas VP, Mihalcea R, Morency LP (2013) Multimodal sentiment analysis of spanish online videos. IEEE Intell Syst 28(3):38\u201345. https:\/\/doi.org\/10.1109\/MIS.2013.9","journal-title":"IEEE Intell Syst"},{"key":"11401_CR67","doi-asserted-by":"crossref","unstructured":"Rossetto L, Giangreco I, Gasser R, Schuldt H (2018) Content-based multimedia retrieval using vitrivr. ACM SIGMultimedia Rec 9(3):8:8\u20138:8. 10.1145\/3178422.3178430\u00a0","DOI":"10.1145\/3178422.3178430"},{"key":"11401_CR68","doi-asserted-by":"publisher","unstructured":"Rudinac S, Larson M, Hanjalic A (2010) Exploiting result consistency to select query expansions for spoken content retrieval. In: Gurrin C, He Y, Kazai G, Kruschwitz U, Little S, Roelleke T, R\u00fcger S, van Rijsbergen K (eds) Advances in Information Retrieval, Lecture Notes in Computer Science, vol 5993, Springer Berlin Heidelberg, Berlin, Heidelberg, pp 645\u2013 648. https:\/\/doi.org\/10.1007\/978-3-642-12275-0_67","DOI":"10.1007\/978-3-642-12275-0_67"},{"key":"11401_CR69","unstructured":"Saita J (2018) Ok google: How to do speech recognition? https:\/\/towardsdatascience.com\/ok-google-how-to-do-speechrecognition-f77b5d7cbe0b"},{"issue":"11","key":"11401_CR70","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1145\/361219.361220","volume":"18","author":"G Salton","year":"1975","unstructured":"Salton G, Wong A, Yang CS (1975) A vector space model for automatic indexing. Commun ACM 18(11):613\u2013620. https:\/\/doi.org\/10.1145\/361219.361220","journal-title":"Commun ACM"},{"key":"11401_CR71","doi-asserted-by":"publisher","unstructured":"Schoeffmann K, Beecks C, Lux M, Uysal MS, Seidl T (2016) Content based retrieval in videos from laparoscopic surgery. In: Webster RJ, Yaniv ZR (eds) Medical Imaging 2016: Image-Guided Procedures, Robotic Interventions, and Modeling, Proceedings of SPIE, vol 9786, SPIE, Bellingham, The United States of America, pp 9786\u20139786\u201310. https:\/\/doi.org\/10.1117\/12.2216864","DOI":"10.1117\/12.2216864"},{"issue":"3","key":"11401_CR72","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1109\/TCSVT.2013.2276700","volume":"24","author":"L Shao","year":"2014","unstructured":"Shao L, Jones S, Li X (2014) Efficient search and localization of human actions in video databases. IEEE Trans Circuits Syst Video Technol 24(3):504\u2013512. https:\/\/doi.org\/10.1109\/TCSVT.2013.2276700","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"11401_CR73","unstructured":"Sharma R, Mummareddy S, Hershey J, Jung N (2013) Method and system for analyzing shopping behavior in a store by associating RFID data with video-based behavior and segmentation data. Patent US 8380558\u00a0"},{"issue":"3","key":"11401_CR74","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1109\/TASLP.2017.2651361","volume":"25","author":"I Sheikh","year":"2017","unstructured":"Sheikh I, Fohr D, Illina I, Linars G (2017) Modelling semantic context of oov words in large vocabulary continuous speech recognition. IEEE\/ACM Trans Audio Speech Lang Process 25(3):598\u2013610. https:\/\/doi.org\/10.1109\/TASLP.2017.2651361","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"11401_CR75","unstructured":"Silva CPA (2010) A speech recognition software for Brazilian Portuguese (in Portuguese). Master\u2019s thesis, Par\u00e1 Federal University, Bel\u00e9m, Brazil\u00a0"},{"key":"11401_CR76","first-page":"90","volume-title":"Narrative-driven multimedia tagging and retrieval: Investigating design and practice for speech-based mobile applications","author":"A Singh","year":"2013","unstructured":"Singh A, Larson M (2013) Narrative-driven multimedia tagging and retrieval: Investigating design and practice for speech-based mobile applications. Language and Audio in Multimedia, In Workshop on Speech, pp 90\u201395"},{"key":"11401_CR77","unstructured":"Singhal A (2001) Modern information retrieval: A brief overview. Bull IEEE Comput Soc Technical Comm Data Eng 24(4):35\u201343"},{"issue":"4","key":"11401_CR78","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1109\/TPAMI.2008.111","volume":"31","author":"J Sivic","year":"2009","unstructured":"Sivic J, Zisserman A (2009) Efficient visual search of videos cast as text retrieval. IEEE Trans Pattern Anal Mach Intell 31(4):591\u2013606. https:\/\/doi.org\/10.1109\/TPAMI.2008.111","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11401_CR79","doi-asserted-by":"publisher","unstructured":"Spola\u00f4r N, Lee HD, Takaki WSR, Ensina LA, Coy CSR, Wu FC (2020) A systematic review on content-based video retrieval. Eng Appl Artif Intel 90:103557. https:\/\/doi.org\/10.1016\/j.engappai.2020.103557","DOI":"10.1016\/j.engappai.2020.103557"},{"issue":"2","key":"11401_CR80","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/s10579-016-9372-5","volume":"51","author":"R Sprugnoli","year":"2017","unstructured":"Sprugnoli R, Moretti G, Bentivogli L, Giuliani D (2017) Creating a ground truth multilingual dataset of news and talk show transcriptions through crowdsourcing. Lang Resour Eval 51(2):283\u2013317. https:\/\/doi.org\/10.1007\/s10579-016-9372-5","journal-title":"Lang Resour Eval"},{"key":"11401_CR81","doi-asserted-by":"publisher","unstructured":"Tahayna B, Ayyasamy RK, Alhashmi S, Eu-Gene S (2010) A novel weighting scheme for efficient document indexing and classification. In: International Symposium on Information Technology, IEEE, New York, The United States of America, vol 2, pp 783-788. https:\/\/doi.org\/10.1109\/ITSIM.2010.5561553","DOI":"10.1109\/ITSIM.2010.5561553"},{"key":"11401_CR82","doi-asserted-by":"publisher","unstructured":"Vigneshwari G, Juliet ANM (2015) Optimized searching of video based on speech and video text content. In: International Conference on Soft-Computing and Networks Security, IEEE, New York, The United States of America, pp 1\u20134. https:\/\/doi.org\/10.1109\/ICSNS.2015.7292369","DOI":"10.1109\/ICSNS.2015.7292369"},{"issue":"11","key":"11401_CR83","doi-asserted-by":"publisher","first-page":"e247","DOI":"10.2196\/jmir.5072","volume":"17","author":"M Vogel","year":"2015","unstructured":"Vogel M, Kaisers W, Wassmuth R, Mayatepek E (2015) Analysis of documentation speed using web-based medical speech recognition technology: Randomized controlled trial. J M\u00e9d Internet Res 17(11):e247. https:\/\/doi.org\/10.2196\/jmir.5072","journal-title":"J M\u00e9d Internet Res"},{"key":"11401_CR84","doi-asserted-by":"crossref","unstructured":"Waheed K, Weaver K, Salam FM (2002) A robust algorithm for detecting speech segments using an entropic contrast. In: The Midwest Symposium on Circuits and Systems, IEEE, Tulsa, The United States of America, pp III\u2013328\u2013III\u2013331","DOI":"10.1109\/MWSCAS.2002.1187039"},{"issue":"3","key":"11401_CR85","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1007\/s13042-015-0426-6","volume":"9","author":"X Wang","year":"2018","unstructured":"Wang X, Yang C, Guan R (2018) A comparative study for biomedical named entity recognition. Int J Mach Learn Cyber 9(3):373\u2013382. https:\/\/doi.org\/10.1007\/s13042-015-0426-6","journal-title":"Int J Mach Learn Cyber"},{"issue":"1","key":"11401_CR86","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/TCSVT.2011.2105597","volume":"21","author":"XY Wei","year":"2011","unstructured":"Wei XY, Jiang YG, Ngo CW (2011) Concept-driven multi-modality fusion for video search. IEEE Trans Circuits Syst Video Technol 21(1):62\u201373. https:\/\/doi.org\/10.1109\/TCSVT.2011.2105597","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"7","key":"11401_CR87","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1002\/(SICI)1097-4571","volume":"49","author":"MJ Witbrock","year":"1998","unstructured":"Witbrock MJ, Hauptmann AG (1998) Speech recognition for a digital video library. J Am Soc Inf Sci Technol 49(7):619\u2013632. https:\/\/doi.org\/10.1002\/(SICI)1097-4571","journal-title":"J Am Soc Inf Sci Technol"},{"key":"11401_CR88","unstructured":"Wu FC, Lee HD, Coy CSR, Fagundes JJ, Ferrero CA, Machado RB, Maletzke AG, Zalewski W, Leal RF, Ayrizono MLS, Costa LHD (2010) Method to map textual documents into structured databases using ontologies (in Portuguese). Patent BR INPI 01810036941"},{"issue":"2","key":"11401_CR89","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/TLT.2014.2307305","volume":"7","author":"H Yang","year":"2014","unstructured":"Yang H, Meinel C (2014) Content based lecture video retrieval using speech and video text information. IEEE Trans Learn Technol 7(2):142\u2013154","journal-title":"IEEE Trans Learn Technol"},{"key":"11401_CR90","doi-asserted-by":"crossref","unstructured":"Yang H, Meinel C (2014) Content based lecture video retrieval using speech and video text information. IEEE Trans Learn Technol 7(2):142\u2013154","DOI":"10.1109\/TLT.2014.2307305"},{"key":"11401_CR91","doi-asserted-by":"publisher","unstructured":"Yin Y, Seo B, Zimmermann R (2015) Content vs. context: Visual and geographic information use in video landmark retrieval. ACM Trans Multimedia Comput Commun Appl 11(3):39:1\u201339:21. https:\/\/doi.org\/10.1145\/2700287","DOI":"10.1145\/2700287"},{"key":"11401_CR92","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-5779-3","volume-title":"Automatic Speech Recognition: A Deep Learning Approach","author":"D Yu","year":"2015","unstructured":"Yu D, Deng L (2015) Automatic Speech Recognition: A Deep Learning Approach. Springer-Verlag, London, London, United Kingdom"},{"key":"11401_CR93","doi-asserted-by":"publisher","unstructured":"Zhai Y, Liu J, Shah M (2006) Automatic query expansion for news video retrieval. In: IEEE International Conference on Multimedia and Expo, IEEE, New York, The United States of America, pp 965\u2013968. https:\/\/doi.org\/10.1109\/ICME.2006.262693","DOI":"10.1109\/ICME.2006.262693"},{"issue":"e1","key":"11401_CR94","doi-asserted-by":"publisher","first-page":"e34","DOI":"10.1093\/jamia\/ocv123","volume":"23","author":"B Zhao","year":"2016","unstructured":"Zhao B, Xu S, Lin S, Luo X, Duan L (2016) A new visual navigation system for exploring biomedical open educational resource (OER) videos. J Am Med Inform Assoc 23(e1):e34\u2013e41. https:\/\/doi.org\/10.1093\/jamia\/ocv123","journal-title":"J Am Med Inform Assoc"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11401-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-11401-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11401-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T23:56:43Z","timestamp":1699401403000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-11401-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,30]]},"references-count":94,"journal-issue":{"issue":"25","published-print":{"date-parts":[[2021,10]]}},"alternative-id":["11401"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-11401-1","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,30]]},"assertion":[{"value":"22 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 July 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 August 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 August 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}