{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T03:16:55Z","timestamp":1774927015375,"version":"3.50.1"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2018,6,25]],"date-time":"2018-06-25T00:00:00Z","timestamp":1529884800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2019,1]]},"DOI":"10.1007\/s11042-018-6276-y","type":"journal-article","created":{"date-parts":[[2018,6,25]],"date-time":"2018-06-25T14:09:21Z","timestamp":1529935761000},"page":"1495-1510","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Spoken keyword search system using improved ASR engine and novel template-based keyword scoring"],"prefix":"10.1007","volume":"78","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4504-3146","authenticated-orcid":false,"given":"Ilyes","family":"Rebai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yassine Ben","family":"Ayed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Walid","family":"Mahdi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,6,25]]},"reference":[{"key":"6276_CR1","doi-asserted-by":"crossref","unstructured":"Abdullah A, Veltkamp R, Wiering M (2009) An ensemble of deep support vector machines for image categorization. In: International Conference of soft computing and pattern recognition (SOCPAR), pp 301\u2013306","DOI":"10.1109\/SoCPaR.2009.67"},{"key":"6276_CR2","doi-asserted-by":"crossref","unstructured":"Allauzen C, Mohri M, Saraclar M (2004) General indexation of weighted automata: application to spoken utterance retrieval. In: Proceedings of the workshop on interdisciplinary approaches to speech indexing and retrieval at HLT-NAACL 2004. Association for Computational Linguistics, pp 33\u201340","DOI":"10.3115\/1626307.1626314"},{"key":"6276_CR3","doi-asserted-by":"crossref","unstructured":"Banfield RE, Hall LO, Bowyer KW, Kegelmeyer WP (2007) A comparison of decision tree ensemble creation techniques. IEEE Trans Pattern Anal Mach Intell, 29(1)","DOI":"10.1109\/TPAMI.2007.250609"},{"issue":"8","key":"6276_CR4","doi-asserted-by":"publisher","first-page":"2338","DOI":"10.1109\/TASL.2011.2134087","volume":"19","author":"D Can","year":"2011","unstructured":"Can D, Saraclar M (2011) Lattice indexing for spoken term detection. IEEE Trans Audio Speech Language Process 19(8):2338\u20132347","journal-title":"IEEE Trans Audio Speech Language Process"},{"issue":"4","key":"6276_CR5","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1080\/19479832.2010.485935","volume":"1","author":"X Ceamanos","year":"2010","unstructured":"Ceamanos X, Waske B, Benediktsson JA, Chanussot J, Fauvel M, Sveinsson JR (2010) A classifier ensemble based on fusion of support vector machines for classifying hyperspectral data. Int J Image Data Fusion 1(4):293\u2013307","journal-title":"Int J Image Data Fusion"},{"key":"6276_CR6","doi-asserted-by":"crossref","unstructured":"Chen G, Parada C, Heigold G (2014) Small-footprint keyword spotting using deep neural networks. In: International Conference on, acoustics, speech, and signal processing (ICASSP), pp 4087\u20134091","DOI":"10.1109\/ICASSP.2014.6854370"},{"key":"6276_CR7","doi-asserted-by":"crossref","unstructured":"Chen G, Parada C, Sainath TN (2015) Query-by-example keyword spotting using long short-term memory networks. In: International Conference on, acoustics, speech, and signal processing (ICASSP), pp 5236\u20135240","DOI":"10.1109\/ICASSP.2015.7178970"},{"issue":"1","key":"6276_CR8","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"GE Dahl","year":"2012","unstructured":"Dahl GE, Yu D, Deng L, Acero A (2012) Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans Audio Speech, Lang Process 20(1):30\u201342","journal-title":"IEEE Trans Audio Speech, Lang Process"},{"key":"6276_CR9","doi-asserted-by":"crossref","unstructured":"Deng L, Yu D, Platt J (2012) Scalable stacking and learning for building deep architectures. In: IEEE International Conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 2133\u20132136","DOI":"10.1109\/ICASSP.2012.6288333"},{"key":"6276_CR10","doi-asserted-by":"crossref","unstructured":"Deng L, Li J, Huang JT, Yao K, Yu D, Seide F, Seltzer M, Zweig G, He X, Williams J et al (2013) Recent advances in deep learning for speech research at microsoft. In: 2013 IEEE International Conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 8604\u20138608","DOI":"10.1109\/ICASSP.2013.6639345"},{"key":"6276_CR11","unstructured":"Fiscus JG, Ajot J, Garofolo JS, Doddingtion G (2007) Results of the 2006 spoken term detection evaluation. In: Proc. sigir, vol 7, pp 51\u201357"},{"key":"6276_CR12","doi-asserted-by":"crossref","unstructured":"Graves A, Jaitly N, Mohamed Ar (2013) Hybrid speech recognition with deep bidirectional lstm. In: 2013 IEEE Workshop on automatic speech recognition and understanding (ASRU). IEEE, pp 273\u2013278","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"6276_CR13","doi-asserted-by":"crossref","unstructured":"Graves A, Mohamed AR, Hinton G (2013) Speech recognition with deep recurrent neural networks. In: 2013 IEEE international conference on acoustics, speech and signal processing (icassp). IEEE, pp 6645\u20136649","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"6276_CR14","unstructured":"Jaitly N, Hinton GE (2013) Vocal tract length perturbation (vtlp) improves speech recognition. In: ICML Workshop on deep learning for audio, speech and language"},{"key":"6276_CR15","doi-asserted-by":"crossref","unstructured":"Jaitly N, Nguyen P, Senior AW, Vanhoucke V (2012) Application of pretrained deep neural networks to large vocabulary speech recognition. In: Interspeech, pp 2578\u20132581","DOI":"10.21437\/Interspeech.2012-10"},{"key":"6276_CR16","doi-asserted-by":"crossref","unstructured":"Karakos D, Schwartz R, Tsakalidis S, Zhang L, Ranjan S, Ng TT, Hsiao R, Saikumar G, Bulyko I, Nguyen L et al (2013) Score normalization and system combination for improved keyword spotting. In: 2013 IEEE Workshop on automatic speech recognition and understanding (ASRU). IEEE, pp 210\u2013215","DOI":"10.1109\/ASRU.2013.6707731"},{"key":"6276_CR17","doi-asserted-by":"crossref","unstructured":"Ko T, Peddinti V, Povey D, Khudanpur S (2015) Audio augmentation for speech recognition. In: INTERSPEECH, pp 3586\u20133589","DOI":"10.21437\/Interspeech.2015-711"},{"key":"6276_CR18","doi-asserted-by":"crossref","unstructured":"Mamou J, Ramabhadran B, Siohan O (2007) Vocabulary independent spoken term detection. In: Proceedings of the 30th annual international ACM SIGIR conference on research and development in information retrieval, pp 615\u2013622","DOI":"10.1145\/1277741.1277847"},{"key":"6276_CR19","doi-asserted-by":"crossref","unstructured":"Mamou J, Cui J, Cui X, Gales MJ, Kingsbury B, Knill K, Mangu L, Nolden D, Picheny M, Ramabhadran B et al (2013) System combination and score normalization for spoken term detection. In: 2013 IEEE International Conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 8272\u20138276","DOI":"10.1109\/ICASSP.2013.6639278"},{"key":"6276_CR20","doi-asserted-by":"crossref","unstructured":"Martin A, Doddington G, Kamm T, Ordowski M, Przybocki M (1997) The det curve in assessment of detection task performance. Tech. rep. National Inst of Standards and Technology Gaithersburg MD","DOI":"10.21437\/Eurospeech.1997-504"},{"key":"6276_CR21","doi-asserted-by":"crossref","unstructured":"Miller DR, Kleber M, Kao CL, Kimball O, Colthurst T, Lowe SA, Schwartz RM, Gish H (2007) Rapid and accurate spoken term detection. In: Eighth Annual Conference of the international speech communication association","DOI":"10.21437\/Interspeech.2007-174"},{"issue":"1","key":"6276_CR22","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/TASL.2011.2109382","volume":"20","author":"AR Mohamed","year":"2012","unstructured":"Mohamed AR, Dahl GE, Hinton G (2012) Acoustic modeling using deep belief networks. IEEE Trans Audio Speech Lang Process 20(1):14\u201322","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"6276_CR23","doi-asserted-by":"crossref","unstructured":"Panayotov V, Chen G, Povey D, Khudanpur S (2015) Librispeech: an asr corpus based on public domain audio books. In: 2015 IEEE International Conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 5206\u20135210","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"6276_CR24","doi-asserted-by":"crossref","unstructured":"Ragni A, Knill KM, Rath SP, Gales MJ (2014) Data augmentation for low resource languages. In: INTERSPEECH, pp 810\u2013814","DOI":"10.21437\/Interspeech.2014-207"},{"key":"6276_CR25","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1016\/j.procs.2017.08.003","volume":"112","author":"I Rebai","year":"2017","unstructured":"Rebai I, BenAyed Y, Mahdi W, Lorr\u00e9 JP (2017) Improving speech recognition using data augmentation and acoustic model fusion. Procedia Comput Sci 112:316\u2013322","journal-title":"Procedia Comput Sci"},{"issue":"61","key":"6276_CR26","first-page":"801","volume":"51","author":"M Saraclar","year":"2004","unstructured":"Saraclar M, Sproat R (2004) Lattice-based search for spoken utterance retrieval. Urbana 51(61):801","journal-title":"Urbana"},{"key":"6276_CR27","doi-asserted-by":"crossref","unstructured":"Siohan O, Bacchiani M (2005) Fast vocabulary-independent audio search using path-based graph indexing. In: Ninth European Conference on speech communication and technology","DOI":"10.21437\/Interspeech.2005-52"},{"key":"6276_CR28","unstructured":"Sz\u00f6ke I, Fapso M, Karafi\u00e1t M, Burget L, Gr\u00e9zl F, Schwarz P, Glembek O, Matejka P, Kont\u00e1r S, Cernocky\u0300 J (2006) But system for nist std 2006-english. In: NIST Spoken Term detection evaluation workshop"},{"key":"6276_CR29","doi-asserted-by":"crossref","unstructured":"Sz\u00f6ke I, Burget L, Cernocky J, Fapso M (2008) Sub-word modeling of out of vocabulary words in spoken term detection. In: Spoken Language technology workshop, 2008. SLT 2008. IEEE, pp 273\u2013276","DOI":"10.1109\/SLT.2008.4777893"},{"key":"6276_CR30","doi-asserted-by":"crossref","unstructured":"Wang Y, Metze F (2014) An in-depth comparison of keyword specific thresholding and sum-to-one score normalization. Tech. rep., Carnegie Mellon University","DOI":"10.21437\/Interspeech.2014-525"},{"issue":"1","key":"6276_CR31","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1007\/s10916-017-0845-x","volume":"42","author":"SH Wang","year":"2018","unstructured":"Wang SH, Lv YD, Sui Y, Liu S, Wang SJ, Zhang YD (2018) Alcoholism detection by data augmentation and convolutional neural network with stochastic pooling. J Med Syst 42(1):2","journal-title":"J Med Syst"},{"issue":"2","key":"6276_CR32","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/S0893-6080(05)80023-1","volume":"5","author":"D Wolpert","year":"1992","unstructured":"Wolpert D (1992) Stacked generalization. IEEE Trans Neural Netw 5(2):241\u2013259","journal-title":"IEEE Trans Neural Netw"},{"key":"6276_CR33","unstructured":"Xu H, Chen NF, Sivadas S, Lim BP, Chng ES, Li H et al (2014) Discriminative score normalization for keyword search decision. In: IEEE International Conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 7078\u20137082"},{"key":"6276_CR34","unstructured":"Yu RP, Thambiratnam K, Seide F (2008) Word-lattice based spoken-document indexing with standard text indexers. In: Searching Spontaneous conversational speech workshop, SIGIR, pp 54\u201361"},{"key":"6276_CR35","doi-asserted-by":"crossref","unstructured":"Zhang X, Trmal J, Povey D, Khudanpur S (2014) Improving deep neural network acoustic models using generalized maxout networks. In: 2014 IEEE International Conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 215\u2013219","DOI":"10.1109\/ICASSP.2014.6853589"},{"key":"6276_CR36","unstructured":"Zhang YD, Dong Z, Chen X, Jia W, Du S, Muhammad K, Wang SH (2017) Image based fruit category classification by 13-layer deep convolutional neural network and data augmentation. Multimed Tools Appl, 1\u201320"},{"key":"6276_CR37","doi-asserted-by":"crossref","unstructured":"Zhang YD, Muhammad K, Tang C (2018) Twelve-layer deep convolutional neural network with stochastic pooling for tea category classification on gpu platform. Multimed Tools Appl, 1\u201319","DOI":"10.1007\/s11042-018-5765-3"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-018-6276-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6276-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6276-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T08:59:56Z","timestamp":1661504396000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-6276-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,25]]},"references-count":37,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2019,1]]}},"alternative-id":["6276"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-6276-y","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,6,25]]},"assertion":[{"value":"17 November 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 April 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 June 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}