{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T13:17:28Z","timestamp":1740143848134,"version":"3.37.3"},"reference-count":137,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,7,19]],"date-time":"2019-07-19T00:00:00Z","timestamp":1563494400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2019,7,19]],"date-time":"2019-07-19T00:00:00Z","timestamp":1563494400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100008425","name":"Conseller\\'{i}a de Cultura, Educaci\\'{o}n e Ordenaci\\'{o}n Universitaria, Xunta de Galicia","doi-asserted-by":"publisher","award":["--------"],"award-info":[{"award-number":["--------"]}],"id":[{"id":"10.13039\/501100008425","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1186\/s13636-019-0156-x","type":"journal-article","created":{"date-parts":[[2019,7,19]],"date-time":"2019-07-19T13:03:00Z","timestamp":1563541380000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Search on speech from spoken queries: the Multi-domain International ALBAYZIN 2018 Query-by-Example Spoken Term Detection Evaluation"],"prefix":"10.1186","volume":"2019","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7699-5620","authenticated-orcid":false,"given":"Javier","family":"Tejedor","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Doroteo T.","family":"Toledano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paula","family":"Lopez-Otero","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laura","family":"Docio-Fernandez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mikel","family":"Pe\u00f1agarikano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luis Javier","family":"Rodriguez-Fuentes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio","family":"Moreno-Sandoval","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,7,19]]},"reference":[{"issue":"3","key":"156_CR1","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1016\/S0167-6393(00)00008-X","volume":"32","author":"K. Ng","year":"2000","unstructured":"K. Ng, V. W. Zue, Subword-based approaches for spoken document retrieval. Speech Commun.32(3), 157\u2013186 (2000).","journal-title":"Speech Commun."},{"issue":"9","key":"156_CR2","doi-asserted-by":"publisher","first-page":"2602","DOI":"10.1109\/TASL.2012.2208628","volume":"20","author":"B. Chen","year":"2012","unstructured":"B. Chen, K. -Y. Chen, P. -N. Chen, Y. -W. Chen, Spoken document retrieval with unsupervised query modeling techniques. IEEE Trans. Audio Speech Lang. Process.20(9), 2602\u20132612 (2012).","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"156_CR3","first-page":"466","volume-title":"Proc. of ASRU","author":"T. -H. Lo","year":"2017","unstructured":"T. -H. Lo, Y. -W. Chen, K. -Y. Chen, H. -M. Wang, B. Chen, in Proc. of ASRU. Neural relevance-aware query modeling for spoken document retrieval (IEEEUSA, 2017), pp. 466\u2013473."},{"key":"156_CR4","first-page":"2037","volume-title":"Proc. of LREC","author":"W. F. L. Heeren","year":"2008","unstructured":"W. F. L. Heeren, F. M. G. de Jong, L. B. van der Werff, M. A. H. Huijbregts, R. J. F. Ordelman, in Proc. of LREC. Evaluation of spoken document retrieval for historic speech collections (ELRABelgium, 2008), pp. 2037\u20132041."},{"issue":"2","key":"156_CR5","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1109\/TASL.2011.2163512","volume":"20","author":"Y. -C. Pan","year":"2012","unstructured":"Y. -C. Pan, H. -Y. Lee, L. -S. Lee, Interactive spoken document retrieval with suggested key terms ranked by a Markov decision process. IEEE Trans. Audio Speech Lang. Process.20(2), 632\u2013645 (2012).","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"156_CR6","doi-asserted-by":"publisher","first-page":"2889","DOI":"10.21437\/Interspeech.2017-612","volume-title":"Proc. of Interspeech","author":"Y. -W. Chen","year":"2017","unstructured":"Y. -W. Chen, K. -Y. Chen, H. -M. Wang, B. Chen, in Proc. of Interspeech. Exploring the use of significant words language modeling for spoken document retrieval (ISCAFrance, 2017), pp. 2889\u20132893."},{"key":"156_CR7","first-page":"425","volume-title":"Proc. of ICASSP","author":"P. Gao","year":"2007","unstructured":"P. Gao, J. Liang, P. Ding, B. Xu, in Proc. of ICASSP. A novel phone-state matrix based vocabulary-independent keyword spotting method for spontaneous speech (IEEEUSA, 2007), pp. 425\u2013428."},{"key":"156_CR8","doi-asserted-by":"crossref","first-page":"1832","DOI":"10.21437\/Interspeech.2012-498","volume-title":"Proc. of Interspeech","author":"B. Zhang","year":"2012","unstructured":"B. Zhang, R. Schwartz, S. Tsakalidis, L. Nguyen, S. Matsoukas, in Proc. of Interspeech. White listing and score normalization for keyword spotting of noisy speech (ISCAFrance, 2012), pp. 1832\u20131835."},{"key":"156_CR9","doi-asserted-by":"crossref","first-page":"15","DOI":"10.21437\/Interspeech.2013-4","volume-title":"Proc. of Interspeech","author":"A. Mandal","year":"2013","unstructured":"A. Mandal, J. van Hout, Y. -C. Tam, V. Mitra, Y. Lei, J. Zheng, D. Vergyri, L. Ferrer, M. Graciarena, A. Kathol, H. Franco, in Proc. of Interspeech. Strategies for high accuracy keyword detection in noisy channels (ISCAFrance, 2013), pp. 15\u201319."},{"key":"156_CR10","first-page":"959","volume-title":"Proc. of Interspeech","author":"T. Ng","year":"2014","unstructured":"T. Ng, R. Hsiao, L. Zhang, D. Karakos, S. H. Mallidi, M. Karafiat, K. Vesely, I. Szoke, B. Zhang, L. Nguyen, R. Schwartz, in Proc. of Interspeech. Progress in the BBN keyword search system for the DARPA RATS program (ISCAFrance, 2014), pp. 959\u2013963."},{"key":"156_CR11","first-page":"7143","volume-title":"Proc. of ICASSP","author":"V. Mitra","year":"2014","unstructured":"V. Mitra, J. van Hout, H. Franco, D. Vergyri, Y. Lei, M. Graciarena, Y. -C. Tam, J. Zheng, in Proc. of ICASSP. Feature fusion for high-accuracy keyword spotting (IEEEUSA, 2014), pp. 7143\u20137147."},{"key":"156_CR12","doi-asserted-by":"publisher","first-page":"760","DOI":"10.21437\/Interspeech.2016-1485","volume-title":"Proc. of Interspeech","author":"S. Panchapagesan","year":"2016","unstructured":"S. Panchapagesan, M. Sun, A. Khare, S. Matsoukas, A. Mandal, B. Hoffmeister, S. Vitaladevuni, in Proc. of Interspeech. Multi-task learning and weighted cross-entropy for DNN-based keyword spotting (ISCAFrance, 2016), pp. 760\u2013764."},{"key":"156_CR13","first-page":"615","volume-title":"Proc. of ACM SIGIR","author":"J. Mamou","year":"2007","unstructured":"J. Mamou, B. Ramabhadran, O. Siohan, in Proc. of ACM SIGIR. Vocabulary independent spoken term detection (ACMUSA, 2007), pp. 615\u2013622."},{"key":"156_CR14","doi-asserted-by":"crossref","first-page":"697","DOI":"10.21437\/Interspeech.2010-263","volume-title":"Proc. of Interspeech","author":"D. Schneider","year":"2010","unstructured":"D. Schneider, T. Mertens, M. Larson, J. Kohler, in Proc. of Interspeech. Contextual verification for open vocabulary spoken term detection (ISCAFrance, 2010), pp. 697\u2013700."},{"key":"156_CR15","doi-asserted-by":"crossref","first-page":"1269","DOI":"10.21437\/Interspeech.2010-399","volume-title":"Proc. of Interspeech","author":"C. Parada","year":"2010","unstructured":"C. Parada, A. Sethy, M. Dredze, F. Jelinek, in Proc. of Interspeech. A spoken term detection framework for recovering out-of-vocabulary words using the web (ISCAFrance, 2010), pp. 1269\u20131272."},{"key":"156_CR16","first-page":"42","volume-title":"Proc. of Speech Search Workshop at SIGIR","author":"I. Sz\u00f6ke","year":"2008","unstructured":"I. Sz\u00f6ke, M. Faps\u0306o, L. Burget, J. C\u0306ernock\u00fd, in Proc. of Speech Search Workshop at SIGIR. Hybrid word-subword decoding for spoken term detection (ACMUSA, 2008), pp. 42\u201348."},{"key":"156_CR17","first-page":"2474","volume-title":"Proc. of Interspeech","author":"Y. Wang","year":"2014","unstructured":"Y. Wang, F. Metze, in Proc. of Interspeech. An in-depth comparison of keyword specific thresholding and sum-to-one score normalization (ISCAFrance, 2014), pp. 2474\u20132478."},{"key":"156_CR18","first-page":"5331","volume-title":"Proc. of ICASSP","author":"L. Mangu","year":"2015","unstructured":"L. Mangu, G. Saon, M. Picheny, B. Kingsbury, in Proc. of ICASSP. Order-free spoken term detection (IEEEUSA, 2015), pp. 5331\u20135335."},{"key":"156_CR19","first-page":"721","volume-title":"Proc. of MediaEval","author":"A. Buzo","year":"2014","unstructured":"A. Buzo, H. Cucu, C. Burileanu, in Proc. of MediaEval. SpeeD@MediaEval 2014: Spoken term detection with robust multilingual phone recognition (CEURGermany, 2014), pp. 721\u2013722."},{"key":"156_CR20","first-page":"200","volume-title":"Proc. of NTCIR-12","author":"R. Konno","year":"2016","unstructured":"R. Konno, K. Ouchi, M. Obara, Y. Shimizu, T. Chiba, T. Hirota, Y. Itoh, in Proc. of NTCIR-12. An STD system using multiple STD results and multiple rescoring method for NTCIR-12 SpokenQuery &Doc task (Japan Society for Promotion of ScienceJapan, 2016), pp. 200\u2013204."},{"key":"156_CR21","first-page":"791","volume-title":"Proc. of MediaEval","author":"R. Jarina","year":"2013","unstructured":"R. Jarina, M. Kuba, R. Gubka, M. Chmulik, M. Paralic, in Proc. of MediaEval. UNIZA system for the spoken web search task at MediaEval 2013 (CEURGermany, 2013), pp. 791\u2013792."},{"key":"156_CR22","first-page":"1","volume-title":"Proc. of ICME","author":"X. Anguera","year":"2013","unstructured":"X. Anguera, M. Ferrarons, in Proc. of ICME. Memory efficient subsequence DTW for query-by-example spoken term detection (IEEEUSA, 2013), pp. 1\u20136."},{"key":"156_CR23","doi-asserted-by":"crossref","first-page":"2191","DOI":"10.21437\/Interspeech.2008-573","volume-title":"Proc. of Interspeech","author":"H. Lin","year":"2008","unstructured":"H. Lin, A. Stupakov, J. Bilmes, in Proc. of Interspeech. Spoken keyword spotting via multi-lattice alignment (ISCAFrance, 2008), pp. 2191\u20132194."},{"key":"156_CR24","doi-asserted-by":"crossref","first-page":"693","DOI":"10.21437\/Interspeech.2010-262","volume-title":"Proc. of Interspeech","author":"C. Chan","year":"2010","unstructured":"C. Chan, L. Lee, in Proc. of Interspeech. Unsupervised spoken-term detection with spoken queries using segment-based dynamic time warping (ISCAFrance, 2010), pp. 693\u2013696."},{"key":"156_CR25","doi-asserted-by":"publisher","first-page":"2874","DOI":"10.21437\/Interspeech.2017-1592","volume-title":"Proc. of Interspeech","author":"S. Settle","year":"2017","unstructured":"S. Settle, K. Levin, H. Kamper, K. Livescu, in Proc. of Interspeech. Query-by-example search with discriminative neural acoustic word embeddings (ISCAFrance, 2017), pp. 2874\u20132878."},{"key":"156_CR26","doi-asserted-by":"publisher","first-page":"117","DOI":"10.21437\/Interspeech.2018-1436","volume-title":"Proc. of Interspeech","author":"R. Shankar","year":"2018","unstructured":"R. Shankar, C. M. Vikram, S. R. M. Prasanna, in Proc. of Interspeech. Spoken keyword detection using joint DTW-CNN (ISCAFrance, 2018), pp. 117\u2013121."},{"key":"156_CR27","first-page":"861","volume-title":"Proc. of MediaEval","author":"A. Ali","year":"2013","unstructured":"A. Ali, M. A. Clements, in Proc. of MediaEval. Spoken web search using and ergodic hidden Markov model of speech (CEURGermany, 2013), pp. 861\u2013862."},{"key":"156_CR28","first-page":"781","volume-title":"Proc. of MediaEval","author":"A. Caranica","year":"2015","unstructured":"A. Caranica, A. Buzo, H. Cucu, C. Burileanu, in Proc. of MediaEval. SpeeD@MediaEval 2015: Multilingual phone recognition approach to Query By Example STD (CEURGermany, 2015), pp. 781\u2013783."},{"key":"156_CR29","first-page":"761","volume-title":"Proc. of MediaEval","author":"S. Kesiraju","year":"2014","unstructured":"S. Kesiraju, G. Mantena, K. Prahallad, in Proc. of MediaEval. IIIT-H system for MediaEval 2014 QUESST (CEURGermany, 2014), pp. 761\u2013762."},{"key":"156_CR30","first-page":"831","volume-title":"Proc. of MediaEval","author":"M. Ma","year":"2015","unstructured":"M. Ma, A. Rosenberg, in Proc. of MediaEval. CUNY systems for the Query-by-Example search on speech task at MediaEval 2015 (CEURGermany, 2015), pp. 831\u2013833."},{"key":"156_CR31","first-page":"384","volume-title":"Proc. of NTCIR-11","author":"J. Takahashi","year":"2014","unstructured":"J. Takahashi, T. Hashimoto, R. Konno, S. Sugawara, K. Ouchi, S. Oshima, T. Akyu, Y. Itoh, in Proc. of NTCIR-11. An IWAPU STD system for OOV query terms and spoken queries (Japan Society for Promotion of ScienceJapan, 2014), pp. 384\u2013389."},{"key":"156_CR32","first-page":"413","volume-title":"Proc. of NTCIR-11","author":"M. Makino","year":"2014","unstructured":"M. Makino, A. Kai, in Proc. of NTCIR-11. Combining subword and state-level dissimilarity measures for improved spoken term detection in NTCIR-11 SpokenQuery &Doc task (Japan Society for Promotion of ScienceJapan, 2014), pp. 413\u2013418."},{"key":"156_CR33","first-page":"200","volume-title":"Proc. of ASRU","author":"N. Sakamoto","year":"2015","unstructured":"N. Sakamoto, K. Yamamoto, S. Nakagawa, in Proc. of ASRU. Combination of syllable based N-gram search and word search for spoken term detection through spoken queries and IV\/OOV classification (IEEEUSA, 2015), pp. 200\u2013206."},{"key":"156_CR34","first-page":"141","volume-title":"Proc. of MediaEval","author":"J. Hou","year":"2015","unstructured":"J. Hou, V. T. Pham, C. -C. Leung, L. Wang, H. Xu, H. Lv, L. Xie, Z. Fu, C. Ni, X. Xiao, H. Chen, S. Zhang, S. Sun, Y. Yuan, P. Li, T. L. Nwe, S. Sivadas, B. Ma, E. S. Chng, H. Li, in Proc. of MediaEval. The NNI Query-by-Example system for MediaEval 2015 (IEEEUSA, 2015), pp. 141\u2013143."},{"key":"156_CR35","first-page":"451","volume-title":"Proc. of MediaEval","author":"J. Vavrek","year":"2015","unstructured":"J. Vavrek, P. Viszlay, M. Lojka, M. Pleva, J. Juhar, M. Rusko, in Proc. of MediaEval. TUKE at MediaEval 2015 QUESST (CEURGermany, 2015), pp. 451\u2013453."},{"issue":"2","key":"156_CR36","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1109\/TASLP.2014.2387382","volume":"23","author":"H. Wang","year":"2015","unstructured":"H. Wang, T. Lee, C. -C. Leung, B. Ma, H. Li, Acoustic segment modeling with spectral clustering methods. IEEE\/ACM Trans. Audio Speech Lang. Process.23(2), 264\u2013277 (2015).","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"2","key":"156_CR37","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1109\/TASLP.2017.2778948","volume":"26","author":"C. -T. Chung","year":"2018","unstructured":"C. -T. Chung, L. -S. Lee, Unsupervised discovery of structured acoustic tokens with applications to spoken term detection. IEEE\/ACM Trans. Audio Speech Lang. Process.26(2), 394\u2013405 (2018).","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"10","key":"156_CR38","doi-asserted-by":"publisher","first-page":"1914","DOI":"10.1109\/TASLP.2017.2729024","volume":"25","author":"C. -T. Chung","year":"2017","unstructured":"C. -T. Chung, C. -Y. Tsai, C. -H. Liu, L. -S. Lee, Unsupervised iterative deep learning of speech features and acoustic tokens with applications to spoken term detection. IEEE\/ACM Trans. Audio Speech Lang. Process.25(10), 1914\u20131928 (2017).","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"1","key":"156_CR39","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.ipm.2018.09.002","volume":"56","author":"P. Lopez-Otero","year":"2019","unstructured":"P. Lopez-Otero, J. Parapar, A. Barreiro, Efficient query-by-example spoken document retrieval combining phone multigram representation and dynamic time warping. Inf. Process. Manag.56(1), 43\u201360 (2019).","journal-title":"Inf. Process. Manag."},{"issue":"5","key":"156_CR40","doi-asserted-by":"publisher","first-page":"946","DOI":"10.1109\/TASLP.2014.2311322","volume":"22","author":"G. Mantena","year":"2014","unstructured":"G. Mantena, S. Achanta, K. Prahallad, Query-by-example spoken term detection using frequency domain linear prediction and non-segmental dynamic time warping. IEEE\/ACM Trans. Audio Speech Lang. Process.22(5), 946\u2013955 (2014).","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"156_CR41","first-page":"341","volume-title":"Proc. of MediaEval","author":"H. Tulsiani","year":"2015","unstructured":"H. Tulsiani, P. Rao, in Proc. of MediaEval. The IIT-B Query-by-Example system for MediaEval 2015 (CEURGermany, 2015), pp. 341\u2013343."},{"key":"156_CR42","first-page":"771","volume-title":"Proc. of MediaEval","author":"M. Bouallegue","year":"2013","unstructured":"M. Bouallegue, G. Senay, M. Morchid, D. Matrouf, G. Linares, R. Dufour, in Proc. of MediaEval. LIA@MediaEval 2013 spoken web search task: an I-vector based approach (CEURGermany, 2013), pp. 771\u2013772."},{"key":"156_CR43","first-page":"831","volume-title":"Proc. of MediaEval","author":"L. J. Rodriguez-Fuentes","year":"2013","unstructured":"L. J. Rodriguez-Fuentes, A. Varona, M. Penagarikano, G. Bordel, M. Diez, in Proc. of MediaEval. GTTS systems for the SWS task at MediaEval 2013 (CEURGermany, 2013), pp. 831\u2013832."},{"key":"156_CR44","first-page":"8545","volume-title":"Proc. of ICASSP","author":"H. Wang","year":"2013","unstructured":"H. Wang, T. Lee, C. -C. Leung, B. Ma, H. Li, in Proc. of ICASSP. Using parallel tokenizers with DTW matrix combination for low-resource spoken term detection (IEEEUSA, 2013), pp. 8545\u20138549."},{"key":"156_CR45","first-page":"681","volume-title":"Proc. of MediaEval","author":"H. Wang","year":"2013","unstructured":"H. Wang, T. Lee, in Proc. of MediaEval. The CUHK spoken web search system for MediaEval 2013 (CEURGermany, 2013), pp. 681\u2013682."},{"key":"156_CR46","first-page":"741","volume-title":"Proc. of MediaEval","author":"J. Proenca","year":"2014","unstructured":"J. Proenca, A. Veiga, F. Perdig\u00e3o, in Proc. of MediaEval. The SPL-IT query by example search on speech system for MediaEval 2014 (CEURGermany, 2014), pp. 741\u2013742."},{"key":"156_CR47","first-page":"1691","volume-title":"Proc. of EUSIPCO","author":"J. Proenca","year":"2015","unstructured":"J. Proenca, A. Veiga, F. Perdigao, in Proc. of EUSIPCO. Query by example search with segmented dynamic time warping for non-exact spoken queries (SpringerGermany, 2015), pp. 1691\u20131695."},{"key":"156_CR48","first-page":"471","volume-title":"Proc. of MediaEval","author":"J. Proenca","year":"2015","unstructured":"J. Proenca, L. Castela, F. Perdigao, in Proc. of MediaEval. The SPL-IT-UC Query by Example search on speech system for MediaEval 2015 (CEURGermany, 2015), pp. 471\u2013473."},{"key":"156_CR49","doi-asserted-by":"publisher","first-page":"750","DOI":"10.21437\/Interspeech.2016-1276","volume-title":"Proc. of Interspeech","author":"J. Proenca","year":"2016","unstructured":"J. Proenca, F. Perdigao, in Proc. of Interspeech. Segmented dynamic time warping for spoken Query-by-Example search (ISCAFrance, 2016), pp. 750\u2013754."},{"key":"156_CR50","first-page":"521","volume-title":"Proc. of MediaEval","author":"P. Lopez-Otero","year":"2015","unstructured":"P. Lopez-Otero, L. Docio-Fernandez, C. Garcia-Mateo, in Proc. of MediaEval. GTM-UVigo systems for the Query-by-Example search on speech task at MediaEval 2015 (CEURGermany, 2015), pp. 521\u2013523."},{"key":"156_CR51","first-page":"223","volume-title":"Proc. of ASRU","author":"P. Lopez-Otero","year":"2015","unstructured":"P. Lopez-Otero, L. Docio-Fernandez, C. Garcia-Mateo, in Proc. of ASRU. Phonetic unit selection for cross-lingual Query-by-Example spoken term detection (IEEEUSA, 2015), pp. 223\u2013229."},{"key":"156_CR52","first-page":"3680","volume-title":"Proc. of Interspeech","author":"A. Saxena","year":"2015","unstructured":"A. Saxena, B. Yegnanarayana, in Proc. of Interspeech. Distinctive feature based representation of speech for Query-by-Example spoken term detection (ISCAFrance, 2015), pp. 3680\u20133684."},{"key":"156_CR53","doi-asserted-by":"publisher","first-page":"2909","DOI":"10.21437\/Interspeech.2017-1183","volume-title":"Proc. of Interspeech","author":"P. Lopez-Otero","year":"2017","unstructured":"P. Lopez-Otero, L. Docio-Fernandez, C. Garcia-Mateo, in Proc. of Interspeech. Compensating gender variability in query-by-example search on speech using voice conversion (ISCAFrance, 2017), pp. 2909\u20132913."},{"key":"156_CR54","doi-asserted-by":"publisher","first-page":"2067","DOI":"10.21437\/Interspeech.2018-1973","volume-title":"Proc. of Interspeech","author":"A. Asaei","year":"2018","unstructured":"A. Asaei, D. Ram, H. Bourlard, in Proc. of Interspeech. Phonological posterior hashing for query by example spoken term detection (ISCAFrance, 2018), pp. 2067\u20132071."},{"key":"156_CR55","first-page":"721","volume-title":"Proc. of MediaEval","author":"M. Skacel","year":"2015","unstructured":"M. Skacel, I. Sz\u00f6ke, in Proc. of MediaEval. BUT QUESST 2015 system description (CEURGermany, 2015), pp. 721\u2013723."},{"key":"156_CR56","doi-asserted-by":"publisher","first-page":"923","DOI":"10.21437\/Interspeech.2016-313","volume-title":"Proc. of Interspeech","author":"H. Chen","year":"2016","unstructured":"H. Chen, C. -C. Leung, L. Xie, B. Ma, H. Li, in Proc. of Interspeech. Unsupervised bottleneck features for low-resource Query-by-Example spoken term detection (ISCAFrance, 2016), pp. 923\u2013927."},{"key":"156_CR57","first-page":"5645","volume-title":"Proc. of ICASSP","author":"Y. Yuan","year":"2017","unstructured":"Y. Yuan, C. -C. Leung, L. Xie, H. Chen, B. Ma, H. Li, in Proc. of ICASSP. Pairwise learning using multi-lingual bottleneck features for low-resource Query-by-Example spoken term detection (IEEEUSA, 2017), pp. 5645\u20135649."},{"key":"156_CR58","first-page":"48","volume-title":"Proc. of ASRU","author":"J. van Hout","year":"2017","unstructured":"J. van Hout, V. Mitra, H. Franco, C. Bartels, D. Vergyri, in Proc. of ASRU. Tackling unseen acoustic conditions in query-by-example search using time and frequency convolution for multilingual deep bottleneck features (IEEEUSA, 2017), pp. 48\u201354."},{"key":"156_CR59","first-page":"1","volume-title":"Proc. of ASRU","author":"E. Yilmaz","year":"2017","unstructured":"E. Yilmaz, J. van Hout, H. Franco, in Proc. of ASRU. Noise-robust exemplar matching for rescoring query-by-example search (IEEEUSA, 2017), pp. 1\u20137."},{"key":"156_CR60","first-page":"5645","volume-title":"Proc. of ICASSP","author":"Y. Yuan","year":"2017","unstructured":"Y. Yuan, C. -C. Leung, L. Xie, H. Chen, B. Ma, H. Li, in Proc. of ICASSP. Pairwise learning using multi-lingual bottleneck features for low-resource query-by-example spoken term detection (IEEEUSA, 2017), pp. 5645\u20135649."},{"key":"156_CR61","doi-asserted-by":"publisher","first-page":"928","DOI":"10.21437\/Interspeech.2016-315","volume-title":"Proc. of Interspeech","author":"A. H. H. N. Torbati","year":"2016","unstructured":"A. H. H. N. Torbati, J. Picone, in Proc. of Interspeech. A nonparametric bayesian approach for spoken term detection by example query (ISCAFrance, 2016), pp. 928\u2013932."},{"key":"156_CR62","first-page":"1","volume-title":"Proc. of MMSP","author":"A. Popli","year":"2015","unstructured":"A. Popli, A. Kumar, in Proc. of MMSP. Query-by-example spoken term detection using low dimensional posteriorgrams motivated by articulatory classes (IEEEUSA, 2015), pp. 1\u20136."},{"key":"156_CR63","first-page":"1722","volume-title":"Proc. of Interspeech","author":"P. Yang","year":"2014","unstructured":"P. Yang, C. -C. Leung, L. Xie, B. Ma, H. Li, in Proc. of Interspeech. Intrinsic spectral analysis based on temporal context features for query-by-example spoken term detection (ISCAFrance, 2014), pp. 1722\u20131726."},{"key":"156_CR64","first-page":"1742","volume-title":"Proc. of Interspeech","author":"B. George","year":"2014","unstructured":"B. George, A. Saxena, G. Mantena, K. Prahallad, B. Yegnanarayana, in Proc. of Interspeech. Unsupervised query-by-example spoken term detection using bag of acoustic words and non-segmental dynamic time warping (ISCAFrance, 2014), pp. 1742\u20131746."},{"issue":"6","key":"156_CR65","doi-asserted-by":"publisher","first-page":"1126","DOI":"10.1109\/TASLP.2018.2815780","volume":"26","author":"D. Ram","year":"2018","unstructured":"D. Ram, A. Asaei, H. Bourlard, Sparse subspace modeling for query by example spoken term detection. IEEE\/ACM Trans. Audio Speech Lang. Process.26(6), 1126\u20131139 (2018).","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"156_CR66","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.specom.2016.08.003","volume":"84","author":"P. Lopez-Otero","year":"2016","unstructured":"P. Lopez-Otero, L. Docio-Fernandez, C. Garcia-Mateo, Finding relevant features for zero-resource query-by-example search on speech. Speech Commun.84:, 24\u201335 (2016).","journal-title":"Speech Commun."},{"key":"156_CR67","first-page":"421","volume-title":"Proc. of ASRU","author":"T. J. Hazen","year":"2009","unstructured":"T. J. Hazen, W. Shen, C. M. White, in Proc. of ASRU. Query-by-example spoken term detection using phonetic posteriorgram templates (IEEEUSA, 2009), pp. 421\u2013426."},{"key":"156_CR68","first-page":"851","volume-title":"Proc. of MediaEval","author":"A. Abad","year":"2013","unstructured":"A. Abad, R. F. Astudillo, I. Trancoso, in Proc. of MediaEval. The L2F spoken web search system for MediaEval 2013 (CEURGermany, 2013), pp. 851\u2013852."},{"key":"156_CR69","first-page":"621","volume-title":"Proc. of MediaEval","author":"I. Sz\u00f6ke","year":"2014","unstructured":"I. Sz\u00f6ke, M. Sk\u00e1cel, L. Burget, in Proc. of MediaEval. BUT QUESST 2014 system description (CEURGermany, 2014), pp. 621\u2013622."},{"key":"156_CR70","first-page":"7849","volume-title":"Proc. of ICASSP","author":"I. Sz\u00f6ke","year":"2014","unstructured":"I. Sz\u00f6ke, L. Burget, F. Gr\u00e9zl, J. H. \u010cernock\u00fd, L. Ondel, in Proc. of ICASSP. Calibration and fusion of query-by-example systems - BUT SWS 2013 (IEEEUSA, 2014), pp. 7849\u20137853."},{"key":"156_CR71","doi-asserted-by":"crossref","first-page":"20","DOI":"10.21437\/Interspeech.2013-5","volume-title":"Proc. of Interspeech","author":"A. Abad","year":"2013","unstructured":"A. Abad, L. J. Rodr\u00edguez-Fuentes, M. Penagarikano, A. Varona, G. Bordel, in Proc. of Interspeech. On the calibration and fusion of heterogeneous spoken term detection systems (ISCAFrance, 2013), pp. 20\u201324."},{"key":"156_CR72","first-page":"691","volume-title":"Proc. of MediaEval","author":"P. Yang","year":"2014","unstructured":"P. Yang, H. Xu, X. Xiao, L. Xie, C. -C. Leung, H. Chen, J. Yu, H. Lv, L. Wang, S. J. Leow, B. Ma, E. S. Chng, H. Li, in Proc. of MediaEval. The NNI query-by-example system for MediaEval 2014 (CEURGermany, 2014), pp. 691\u2013692."},{"key":"156_CR73","doi-asserted-by":"publisher","first-page":"3703","DOI":"10.21437\/Interspeech.2016-691","volume-title":"Proc. of Interspeech","author":"C. -C. Leung","year":"2016","unstructured":"C. -C. Leung, L. Wang, H. Xu, J. Hou, V. T. Pham, H. Lv, L. Xie, X. Xiao, C. Ni, B. Ma, E. S. Chng, H. Li, in Proc. of Interspeech. Toward high-performance language-independent Query-by-Example spoken term detection for MediaEval 2015: Post-Evaluation analysis (ISCAFrance, 2016), pp. 3703\u20133707."},{"key":"156_CR74","first-page":"6030","volume-title":"Proc. of ICASSP","author":"H. Xu","year":"2016","unstructured":"H. Xu, J. Hou, X. Xiao, V. T. Pham, C. -C. Leung, L. Wang, V. H. Do, H. Lv, L. Xie, B. Ma, E. S. Chng, H. Li, in Proc. of ICASSP. Approximate search of audio queries by using DTW with phone time boundary and data augmentation (IEEEUSA, 2016), pp. 6030\u20136034."},{"key":"156_CR75","first-page":"205","volume-title":"Proc. of NTCIR-12","author":"S. Oishi","year":"2016","unstructured":"S. Oishi, T. Matsuba, M. Makino, A. Kai, in Proc. of NTCIR-12. Combining state-level and DNN-based acoustic matches for efficient spoken term detection in NTCIR-12 SpokenQuery &Doc-2 task (Japan Society for Promotion of ScienceJapan, 2016), pp. 205\u2013210."},{"key":"156_CR76","doi-asserted-by":"publisher","first-page":"740","DOI":"10.21437\/Interspeech.2016-1259","volume-title":"Proc. of Interspeech","author":"S. Oishi","year":"2016","unstructured":"S. Oishi, T. Matsuba, M. Makino, A. Kai, in Proc. of Interspeech. Combining state-level spotting and posterior-based acoustic match for improved query-by-example spoken term detection (ISCAFrance, 2016), pp. 740\u2013744."},{"key":"156_CR77","doi-asserted-by":"publisher","first-page":"1918","DOI":"10.21437\/Interspeech.2016-309","volume-title":"Proc. of Interspeech","author":"M. Obara","year":"2016","unstructured":"M. Obara, K. Kojima, K. Tanaka, S. -W. Lee, Y. Itoh, in Proc. of Interspeech. Rescoring by combination of posteriorgram score and subword-matching score for use in Query-by-Example (ISCAFrance, 2016), pp. 1918\u20131922."},{"issue":"1","key":"156_CR78","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1687-4722-2011-1","volume":"2011","author":"B. Taras","year":"2011","unstructured":"B. Taras, C. Nadeu, Audio segmentation of broadcast news in the Albayzin-2010 evaluation: overview, results, and discussion. EURASIP J. Audio Speech Music. Process.2011(1), 1\u201310 (2011).","journal-title":"EURASIP J. Audio Speech Music. Process."},{"issue":"19","key":"156_CR79","first-page":"1","volume":"2012","author":"M. Zelen\u00e1k","year":"2012","unstructured":"M. Zelen\u00e1k, H. Schulz, J. Hernando, Speaker diarization of broadcast news in Albayzin 2010 evaluation campaign. EURASIP J. Audio Speech Music. Process.2012(19), 1\u20139 (2012).","journal-title":"EURASIP J. Audio Speech Music. Process."},{"key":"156_CR80","doi-asserted-by":"crossref","first-page":"1529","DOI":"10.21437\/Interspeech.2011-322","volume-title":"Proc. of Interspeech","author":"L. J. Rodr\u00edguez-Fuentes","year":"2011","unstructured":"L. J. Rodr\u00edguez-Fuentes, M. Penagarikano, A. Varona, M. D\u00edez, G. Bordel, in Proc. of Interspeech. The Albayzin 2010 Language Recognition Evaluation (ISCAFrance, 2011), pp. 1529\u20131532."},{"issue":"21","key":"156_CR81","first-page":"1","volume":"2015","author":"J. Tejedor","year":"2015","unstructured":"J. Tejedor, D. T. Toledano, P. Lopez-Otero, L. Docio-Fernandez, C. Garcia-Mateo, A. Cardenal, J. D. Echeverry-Correa, A. Coucheiro-Limeres, J. Olcoz, A. Miguel, Spoken term detection ALBAYZIN 2014 evaluation: overview, systems, results, and discussion. EURASIP J. Audio Speech Music. Process.2015(21), 1\u201327 (2015).","journal-title":"EURASIP J. Audio Speech Music. Process."},{"issue":"23","key":"156_CR82","first-page":"1","volume":"2013","author":"J. Tejedor","year":"2013","unstructured":"J. Tejedor, D. T. Toledano, X. Anguera, A. Varona, L. F. Hurtado, A. Miguel, J. Col\u00e1s, Query-by-example spoken term detection ALBAYZIN 2012 evaluation: overview, systems, results, and discussion. EURASIP J. Audio Speech Music. Process.2013(23), 1\u201317 (2013).","journal-title":"EURASIP J. Audio Speech Music. Process."},{"issue":"1","key":"156_CR83","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13636-016-0080-2","volume":"2016","author":"J. Tejedor","year":"2016","unstructured":"J. Tejedor, D. T. Toledano, P. Lopez-Otero, L. Docio-Fernandez, C. Garcia-Mateo, Comparison of ALBAYZIN query-by-example spoken term detection 2012 and 2014 evaluations. EURASIP J. Audio Speech Music. Process.2016(1), 1\u201319 (2016).","journal-title":"EURASIP J. Audio Speech Music. Process."},{"issue":"33","key":"156_CR84","first-page":"1","volume":"2015","author":"D. Cast\u00e1n","year":"2015","unstructured":"D. Cast\u00e1n, D. Tavarez, P. Lopez-Otero, J. Franco-Pedroso, H. Delgado, E. Navas, L. Docio-Fern\u00e1ndez, D. Ramos, J. Serrano, A. Ortega, E. Lleida, Albayz\u00edn-2014 evaluation: audio segmentation and classification in broadcast news domains. EURASIP J. Audio Speech Music. Process.2015(33), 1\u20139 (2015).","journal-title":"EURASIP J. Audio Speech Music. Process."},{"key":"156_CR85","first-page":"317","volume-title":"Proc. of FALA","author":"F. M\u00e9ndez","year":"2010","unstructured":"F. M\u00e9ndez, L. Doc\u00edo, M. Arza, F. Campillo, in Proc. of FALA. The Albayzin 2010 text-to-speech evaluation (ISCAFrance, 2010), pp. 317\u2013340."},{"issue":"22","key":"156_CR86","first-page":"1","volume":"2017","author":"J. Tejedor","year":"2017","unstructured":"J. Tejedor, D. T. Toledano, P. Lopez-Otero, L. Docio-Fernandez, L. Serrano, I. Hernaez, A. Coucheiro-Limeres, J. Ferreiros, J. Olcoz, J. Llombart, Albayzin 2016 spoken term detection evaluation: an international open competitive evaluation in spanish. EURASIP J. Audio Speech Music Process.2017(22), 1\u201323 (2017).","journal-title":"EURASIP J. Audio Speech Music Process."},{"issue":"2","key":"156_CR87","first-page":"1","volume":"2018","author":"J. Tejedor","year":"2018","unstructured":"J. Tejedor, D. T. Toledano, P. Lopez-Otero, L. Docio-Fernandez, J. Proen\u00e7a, F. Perdig\u00e3o, F. Garc\u00eda-Granada, E. Sanchis, A. Pompili, A. Abad, Albayzin query-by-example spoken term detection 2016 evaluation. EURASIP J. Audio Speech Music Process.2018(2), 1\u201325 (2018).","journal-title":"EURASIP J. Audio Speech Music Process."},{"key":"156_CR88","doi-asserted-by":"crossref","first-page":"363","DOI":"10.21437\/Eurospeech.1997-139","volume-title":"Proc. of Eurospeech","author":"J. Billa","year":"1997","unstructured":"J. Billa, K. W. Ma, J. W. McDonough, Zavaliagkos, D. R. Miller, K. N. Ross, A. El-Jaroudi, in Proc. of Eurospeech. Multilingual speech recognition: the 1996 Byblos callhome system (ISCAFrance, 1997), pp. 363\u2013366."},{"key":"156_CR89","first-page":"156","volume-title":"Proc. of MICAI","author":"H. Cuayahuitl","year":"2002","unstructured":"H. Cuayahuitl, B. Serridge, in Proc. of MICAI. Out-of-vocabulary word modeling and rejection for spanish keyword spotting systems (SpringerGermany, 2002), pp. 156\u2013165."},{"key":"156_CR90","doi-asserted-by":"crossref","first-page":"3141","DOI":"10.21437\/Eurospeech.2003-785","volume-title":"Proc. of Eurospeech","author":"M. Killer","year":"2003","unstructured":"M. Killer, S. Stuker, T. Schultz, in Proc. of Eurospeech. Grapheme based speech recognition (ISCAFrance, 2003), pp. 3141\u20133144."},{"key":"156_CR91","volume-title":"Contributions to keyword spotting and spoken term detection for information retrieval in audio mining. PhD thesis","author":"J. Tejedor","year":"2009","unstructured":"J. Tejedor, Contributions to keyword spotting and spoken term detection for information retrieval in audio mining. PhD thesis (Universidad Aut\u00f3noma de Madrid, Madrid, 2009)."},{"key":"156_CR92","first-page":"4334","volume-title":"Proc. of ICASSP","author":"L. Burget","year":"2010","unstructured":"L. Burget, P. Schwarz, M. Agarwal, P. Akyazi, K. Feng, A. Ghoshal, O. Glembek, N. Goel, M. Karafiat, D. Povey, A. Rastrow, R. C. Rose, S. Thomas, in Proc. of ICASSP. Multilingual acoustic modeling for speech recognition based on subspace gaussian mixture models (IEEEUSA, 2010), pp. 4334\u20134337."},{"issue":"5","key":"156_CR93","doi-asserted-by":"publisher","first-page":"1083","DOI":"10.1016\/j.csl.2013.09.008","volume":"28","author":"J. Tejedor","year":"2014","unstructured":"J. Tejedor, D. T. Toledano, D. Wang, S. King, J. Col\u00e1s, Feature analysis for discriminative confidence estimation in spoken term detection. Comput. Speech Lang.28(5), 1083\u20131114 (2014).","journal-title":"Comput. Speech Lang."},{"key":"156_CR94","first-page":"1747","volume-title":"Proc. of Interspeech","author":"J. Li","year":"2014","unstructured":"J. Li, X. Wang, B. Xu, in Proc. of Interspeech. An empirical study of multilingual and low-resource spoken term detection using deep neural networks (ISCAFrance, 2014), pp. 1747\u20131751."},{"key":"156_CR95","volume-title":"Student test","author":"M. Hazewinkel","year":"1994","unstructured":"M. Hazewinkel, Student test (Kluwer Academic, Denmark, 1994)."},{"unstructured":"NIST, The spoken term detection (STD) 2006 Evaluation Plan. https:\/\/catalog.ldc.upenn.edu\/docs\/LDC2011S02\/std06-evalplan-v10.pdf . Accessed Apr 2019.","key":"156_CR96"},{"key":"156_CR97","first-page":"45","volume-title":"Proc. of SSCS","author":"J. G. Fiscus","year":"2007","unstructured":"J. G. Fiscus, J. Ajot, J. S. Garofolo, G. Doddingtion, in Proc. of SSCS. Results of the 2006 spoken term detection evaluation (ACMUSA, 2007), pp. 45\u201350."},{"key":"156_CR98","doi-asserted-by":"crossref","first-page":"1895","DOI":"10.21437\/Eurospeech.1997-504","volume-title":"Proc. of Eurospeech","author":"A. Martin","year":"1997","unstructured":"A. Martin, G. Doddingtion, T. Kamm, M. Ordowski, M. Przybocki, in Proc. of Eurospeech. The DET curve in assessment of detection task performance (ISCAFrance, 1997), pp. 1895\u20131898."},{"unstructured":"NIST, Evaluation Toolkit (STDEval) Software. https:\/\/www.nist.gov\/itl\/iad\/mig\/tools . Accessed Apr 2019.","key":"156_CR99"},{"unstructured":"I. T. Union, ITU-T Recommendation P.563: Single-ended method for objective speech quality assessment in narrow-band telephony applications. http:\/\/www.itu.int\/rec\/T-REC-P.563\/en . Accessed Apr 2019.","key":"156_CR100"},{"unstructured":"E. Lleida, A. Ortega, A. Miguel, V. Baz\u00e1n, C. P\u00e9rez, M. Zotano, A. de Prada, RTVE2018 database description. Vivolab and Corporaci\u00f3n Radiotelevisi\u00f3n Espa\u00f1ola, Zaragoza. http:\/\/catedrartve.unizar.es\/reto2018\/RTVE2018DB.pdf . Accessed Apr 2019.","key":"156_CR101"},{"unstructured":"M. V. Matos, Dise\u00f1o y compilaci\u00f3n de un corpus multimodal de an\u00e1lisis pragm\u00e1tico para la aplicaci\u00f3n a la ense\u00f1anza del espa\u00f1ol. PhD thesis Universidad Aut\u00f3noma de Madrid, Madrid, (2017).","key":"156_CR102"},{"key":"156_CR103","first-page":"1","volume-title":"Proc. of MediaEval","author":"N. Rajput","year":"2011","unstructured":"N. Rajput, F. Metze, in Proc. of MediaEval. Spoken web search (CEURGermany, 2011), pp. 1\u20132."},{"key":"156_CR104","first-page":"41","volume-title":"Proc. of MediaEval","author":"F. Metze","year":"2012","unstructured":"F. Metze, E. Barnard, M. Davel, C. van Heerden, X. Anguera, G. Gravier, N. Rajput, in Proc. of MediaEval. The spoken web search task (CEURGermany, 2012), pp. 41\u201342."},{"key":"156_CR105","first-page":"921","volume-title":"Proc. of MediaEval","author":"X. Anguera","year":"2013","unstructured":"X. Anguera, F. Metze, A. Buzo, I. Sz\u00f6ke, L. J. Rodriguez-Fuentes, in Proc. of MediaEval. The spoken web search task (CEURGermany, 2013), pp. 921\u2013922."},{"key":"156_CR106","first-page":"351","volume-title":"Proc. of MediaEval","author":"X. Anguera","year":"2014","unstructured":"X. Anguera, L. J. Rodriguez-Fuentes, I. Sz\u00f6ke, A. Buzo, F. Metze, in Proc. of MediaEval. Query by Example Search on Speech at MediaEval 2014 (CEURGermany, 2014), pp. 351\u2013352."},{"key":"156_CR107","first-page":"81","volume-title":"Proc. of MediaEval","author":"I. Sz\u00f6ke","year":"2015","unstructured":"I. Sz\u00f6ke, L. J. Rodriguez-Fuentes, A. Buzo, X. Anguera, F. Metze, J. Proenca, M. Lojka, X. Xiong, in Proc. of MediaEval. Query by Example Search on Speech at MediaEval 2015 (CEURGermany, 2015), pp. 81\u201382."},{"key":"156_CR108","first-page":"1","volume-title":"Proc. of NTCIR-11","author":"T. Akiba","year":"2014","unstructured":"T. Akiba, H. Nishizaki, H. Nanjo, G. J. F. Jones, in Proc. of NTCIR-11. Overview of the NTCIR-11 spokenquery &doc task (Japan Society for Promotion of ScienceJapan, 2014), pp. 1\u201315."},{"key":"156_CR109","first-page":"1","volume-title":"Proc. of NTCIR-12","author":"T. Akiba","year":"2016","unstructured":"T. Akiba, H. Nishizaki, H. Nanjo, G. J. F. Jones, in Proc. of NTCIR-12. Overview of the NTCIR-12 spokenquery &doc-2 (Japan Society for Promotion of ScienceJapan, 2016), pp. 1\u201313."},{"key":"156_CR110","volume-title":"Phoneme recognition based on long temporal context. PhD thesis","author":"P. Schwarz","year":"2008","unstructured":"P. Schwarz, Phoneme recognition based on long temporal context. PhD thesis (FIT, BUT, Brno, Czech Republic, 2008)."},{"key":"156_CR111","doi-asserted-by":"crossref","first-page":"2901","DOI":"10.21437\/Interspeech.2011-726","volume-title":"Proc. of Interspeech","author":"A. Varona","year":"2011","unstructured":"A. Varona, M. Penagarikano, L. J. Rodr\u00edguez-Fuentes, G. Bordel, in Proc. of Interspeech. On the use of lattices of time-synchronous cross-decoder phone co-occurrences in a SVM-phonotactic language recognition system (ISCAFrance, 2011), pp. 2901\u20132904."},{"key":"156_CR112","first-page":"1459","volume-title":"Proc. of ACM Multimedia (MM)","author":"F. Eyben","year":"2010","unstructured":"F. Eyben, M. Wollmer, B. Schuller, in Proc. of ACM Multimedia (MM). OpenSMILE - the Munich versatile and fast open-source audio feature extractor (ACMUSA, 2010), pp. 1459\u20131462."},{"key":"156_CR113","first-page":"398","volume-title":"Proc. of ASRU","author":"Y. Zhang","year":"2009","unstructured":"Y. Zhang, J. R. Glass, in Proc. of ASRU. Unsupervised spoken keyword spotting via segmental DTW on gaussian posteriorgrams (IEEEUSA, 2009), pp. 398\u2013403."},{"key":"156_CR114","volume-title":"Proc. of ASRU","author":"D. Povey","year":"2011","unstructured":"D. Povey, A. Ghoshal, G. Boulianne, L. Burget, O. Glembek, N. Goel, M. Hannemann, P. Motlicek, Y. Qian, P. Schwarz, J. Silovsky, G. Stemmer, K. Vesely, in Proc. of ASRU. The KALDI speech recognition toolkit (IEEEUSA, 2011)."},{"key":"156_CR115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3","volume-title":"Information retrieval for music and motion","author":"M. Muller","year":"2007","unstructured":"M. Muller, Information retrieval for music and motion (Springer, New York, 2007)."},{"key":"156_CR116","first-page":"621","volume-title":"Proc. of MediaEval","author":"I. Sz\u00f6ke","year":"2014","unstructured":"I. Sz\u00f6ke, M. Skacel, L. Burget, in Proc. of MediaEval. BUT QUESST 2014 system description (CEURGermany, 2014), pp. 621\u2013622."},{"unstructured":"J. Ponte, W. Croft, in Proc. of ACM SIGIR. A language modeling approach to information retrieval, (1998), pp. 275\u2013281.","key":"156_CR117"},{"key":"156_CR118","first-page":"680","volume-title":"Lecture Notes in Computer Science","author":"Javier Parapar","year":"2009","unstructured":"J. Parapar, A. Freire, A. Barreiro, in Proc. of ECIR. Revisiting n-gram based models for retrieval in degraded large collections, (2009), pp. 680\u2013684."},{"unstructured":"E. Rodr\u00edguez-Banga, C. Garcia-Mateo, F. M\u00e9ndez-Paz\u00f3, M. Gonz\u00e1lez-Gonz\u00e1lez, C. Magari\u00f1os, in Proc. of Iberspeech. Cotov\u00eda: an open source TTS for Galician and Spanish, (2012), pp. 308\u2013315.","key":"156_CR119"},{"key":"156_CR120","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to information retrieval","author":"C. Manning","year":"2008","unstructured":"C. Manning, P. Raghavan, H. Schutze, Introduction to information retrieval (Cambridge University Press, Cambridge, 2008)."},{"unstructured":"A. Abad, L. J. Rodr\u00edguez-Fuentes, M. Pe\u00f1agarikano, A. Varona, G. Bordel, in Proc. of Interspeech. On the calibration and fusion of heterogeneous spoken term detection systems, (2013), pp. 20\u201324.","key":"156_CR121"},{"key":"156_CR122","first-page":"1","volume-title":"Proc. of IEEE Odyssey 2006: The Speaker and Language Recognition Workshop","author":"N. Brummer","year":"2006","unstructured":"N. Brummer, D. van Leeuwen, in Proc. of IEEE Odyssey 2006: The Speaker and Language Recognition Workshop. On calibration of language recognition scores (IEEEUSA, 2006), pp. 1\u20138."},{"unstructured":"N. Brummer, E. de Villiers, The BOSARIS Toolkit user guide: theory, algorithms and code for binary classifier score processing (Agnitio Labs. https:\/\/sites.google.com\/site\/nikobrummer . Accessed Apr 2019.","key":"156_CR123"},{"unstructured":"J. Wiseman, Python interface to the WebRTC ( https:\/\/webrtc.org\/ ) voice activity detector (VAD). https:\/\/github.com\/wiseman\/py-webrtcvad . Accessed Apr 2019.","key":"156_CR124"},{"key":"156_CR125","doi-asserted-by":"publisher","first-page":"283","DOI":"10.21437\/Odyssey.2018-40","volume-title":"Proc. of Odyssey","author":"A. Silnova","year":"2018","unstructured":"A. Silnova, P. Matejka, O. Glembek, O. Plchot, O. Novotny, F. Grezl, P. Schwarz, L. Burget, J. H. Cernocky, in Proc. of Odyssey. BUT\/Phonexia bottleneck feature ExtractorIEEEUSA, 2018), pp. 283\u2013287."},{"key":"156_CR126","first-page":"69","volume-title":"Proc. of LREC","author":"C. Cieri","year":"2004","unstructured":"C. Cieri, D. Miller, K. Walker, in Proc. of LREC. The Fisher Corpus: a resource for the next generations of speech-to-text (ELRABelgium, 2004), pp. 69\u201371."},{"unstructured":"Intelligence Advanced Research Projects Activity (IARPA), Babel Program (Intelligence Advanced Research Projects Activity (IARPA). https:\/\/www.iarpa.gov\/index.php\/research-programs\/babel . Accessed Apr 2019.","key":"156_CR127"},{"key":"156_CR128","first-page":"7819","volume-title":"Proc. of ICASSP","author":"L. J. Rodriguez-Fuentes","year":"2014","unstructured":"L. J. Rodriguez-Fuentes, A. Varona, M. Penagarikano, G. Bordel, M. Diez, in Proc. of ICASSP. High-performance query-by-example spoken term detection on the SWS 2013 evaluationIEEEUSA, 2014), pp. 7819\u20137823."},{"key":"156_CR129","doi-asserted-by":"crossref","first-page":"20","DOI":"10.21437\/Interspeech.2013-5","volume-title":"Proc. of Interspeech","author":"A. Abad","year":"2013","unstructured":"A. Abad, L. J. Rodriguez-Fuentes, M. Penagarikano, A. Varona, M. Diez, G. Bordel, in Proc. of Interspeech. On the calibration and fusion of heterogeneous spoken term detection systems (ISCAFrance, 2013), pp. 20\u201324."},{"key":"156_CR130","first-page":"2061","volume-title":"Proc. of LREC","author":"C. Garcia-Mateo","year":"2004","unstructured":"C. Garcia-Mateo, J. Dieguez-Tirado, L. Docio-Fernandez, A. Cardenal-Lopez, in Proc. of LREC. Transcrigal: a bilingual system for automatic indexing of broadcast news (ELRABelgium, 2004), pp. 2061\u20132064."},{"key":"156_CR131","first-page":"224","volume-title":"Proc. of Iberspeech","author":"A. Moreno","year":"2004","unstructured":"A. Moreno, L. Campillos, in Proc. of Iberspeech. MAVIR: a corpus of spontaneous formal speech in spanish and english (ISCAFrance, 2004), pp. 224\u2013230."},{"key":"156_CR132","first-page":"901","volume-title":"Proc. of Interspeech","author":"A. Stolcke","year":"2002","unstructured":"A. Stolcke, in Proc. of Interspeech. SRILM - an extensible language modeling toolkit (ISCAFrance, 2002), pp. 901\u2013904."},{"key":"156_CR133","first-page":"8560","volume-title":"Proc. of ICASSP","author":"G. Chen","year":"2013","unstructured":"G. Chen, S. Khudanpur, D. Povey, J. Trmal, D. Yarowsky, O. Yilmaz, in Proc. of ICASSP. Quantifying the value of pronunciation lexicons for keyword search in low resource languages (IEEEUSA, 2013), pp. 8560\u20138564."},{"key":"156_CR134","first-page":"430","volume-title":"Proc. of SLT","author":"V. T. Pham","year":"2014","unstructured":"V. T. Pham, N. F. Chen, S. Sivadas, H. Xu, I. -F. Chen, C. Ni, E. S. Chng, H. Li, in Proc. of SLT. System and keyword dependent fusion for spoken term detection (IEEEUSA, 2014), pp. 430\u2013435."},{"issue":"8","key":"156_CR135","doi-asserted-by":"publisher","first-page":"2338","DOI":"10.1109\/TASL.2011.2134087","volume":"19","author":"D. Can","year":"2011","unstructured":"D. Can, M. Saraclar, Lattice indexing for spoken term detection. IEEE Trans. Audio Speech Lang. Process.19(8), 2338\u20132347 (2011).","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"156_CR136","first-page":"314","volume-title":"Proc. of Interspeech","author":"D. R. H. Miller","year":"2007","unstructured":"D. R. H. Miller, M. Kleber, C. -L. Kao, O. Kimball, T. Colthurst, S. A. Lowe, R. M. Schwartz, H. Gish, in Proc. of Interspeech. Rapid and accurate spoken term detection (ISCAFrance, 2007), pp. 314\u2013317."},{"key":"156_CR137","first-page":"416","volume-title":"Proc. of ASRU","author":"G. Chen","year":"2013","unstructured":"G. Chen, O. Yilmaz, J. Trmal, D. Povey, S. Khudanpur, in Proc. of ASRU. Using proxies for OOV keywords in the keyword search task (IEEEUSA, 2013), pp. 416\u2013421."}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-019-0156-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13636-019-0156-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-019-0156-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,21]],"date-time":"2024-07-21T05:59:57Z","timestamp":1721541597000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13636-019-0156-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,19]]},"references-count":137,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["156"],"URL":"https:\/\/doi.org\/10.1186\/s13636-019-0156-x","relation":{},"ISSN":["1687-4722"],"issn-type":[{"type":"electronic","value":"1687-4722"}],"subject":[],"published":{"date-parts":[[2019,7,19]]},"assertion":[{"value":"12 April 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 June 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 July 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"13"}}