{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T13:17:43Z","timestamp":1740143863759,"version":"3.37.3"},"reference-count":139,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,9,2]],"date-time":"2019-09-02T00:00:00Z","timestamp":1567382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2019,9,2]],"date-time":"2019-09-02T00:00:00Z","timestamp":1567382400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100010801","name":"Xunta de Galicia","doi-asserted-by":"publisher","award":["GPC ED431B 2016\/035"],"award-info":[{"award-number":["GPC ED431B 2016\/035"]}],"id":[{"id":"10.13039\/501100010801","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010801","name":"Xunta de Galicia","doi-asserted-by":"publisher","award":["GRC 2014\/024"],"award-info":[{"award-number":["GRC 2014\/024"]}],"id":[{"id":"10.13039\/501100010801","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003451","name":"Euskal Herriko Unibertsitatea","doi-asserted-by":"publisher","award":["GIU16\/68"],"award-info":[{"award-number":["GIU16\/68"]}],"id":[{"id":"10.13039\/501100003451","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010198","name":"Ministerio de Econom\u00eda, Industria y Competitividad, Gobierno de Espa\u00f1a","doi-asserted-by":"publisher","award":["TEC2015-68172-C2-1-P"],"award-info":[{"award-number":["TEC2015-68172-C2-1-P"]}],"id":[{"id":"10.13039\/501100010198","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","award":["TIN2015-64282-R"],"award-info":[{"award-number":["TIN2015-64282-R"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","award":["TEC2015-65345-P"],"award-info":[{"award-number":["TEC2015-65345-P"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","award":["ED431G\/01"],"award-info":[{"award-number":["ED431G\/01"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","award":["ED431G\/04"],"award-info":[{"award-number":["ED431G\/04"]}],"id":[{"id":"10.13039\/501100008530","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\/s13636-019-0159-7","type":"journal-article","created":{"date-parts":[[2019,9,2]],"date-time":"2019-09-02T18:08:04Z","timestamp":1567447684000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["ALBAYZIN 2018 spoken term detection evaluation: a multi-domain international evaluation in Spanish"],"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":"Ana R.","family":"Montalvo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose M.","family":"Ramirez","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"}]}],"member":"297","published-online":{"date-parts":[[2019,9,2]]},"reference":[{"issue":"4-5","key":"159_CR1","first-page":"235","volume":"5","author":"M. Larson","year":"2011","unstructured":"M. Larson, G. Jones, Spoken content retrieval: a survey of techniques and technologies. Found. Trends Inf. Retr.5(4-5), 235\u2013422 (2011).","journal-title":"Found. Trends Inf. Retr."},{"issue":"3","key":"159_CR2","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 Comm.32(3), 157\u2013186 (2000).","journal-title":"Speech Comm."},{"issue":"9","key":"159_CR3","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\u201312 (2012).","journal-title":"IEEE Trans. Audio, Speech, Lang. Process."},{"key":"159_CR4","first-page":"466","volume-title":"Proceedings of ASRU","author":"T. -H. Lo","year":"2017","unstructured":"T. -H. Lo, Y. -W. Chen, K. -Y. Chen, H. -M. Wang, B. Chen, in Proceedings of ASRU. Neural relevance-aware query modeling for spoken document retrieval (IEEEUSA, 2017), pp. 466\u2013473."},{"key":"159_CR5","first-page":"2037","volume-title":"Proceedings 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 Proceedings of LREC. Evaluation of spoken document retrieval for historic speech collections (ELRABelgium, 2008), pp. 2037\u20132041."},{"issue":"2","key":"159_CR6","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":"159_CR7","doi-asserted-by":"publisher","first-page":"2889","DOI":"10.21437\/Interspeech.2017-612","volume-title":"Proceedings of Interspeech","author":"Y. -W. Chen","year":"2017","unstructured":"Y. -W. Chen, K. -Y. Chen, H. -M. Wang, B. Chen, in Proceedings of Interspeech. Exploring the use of significant words language modeling for spoken document retrieval (ISCAFrance, 2017), pp. 2889\u20132893."},{"key":"159_CR8","first-page":"425","volume-title":"Proceedings of ICASSP","author":"P. Gao","year":"2007","unstructured":"P. Gao, J. Liang, P. Ding, B. Xu, in Proceedings of ICASSP. A novel phone-state matrix based vocabulary-independent keyword spotting method for spontaneous speech (IEEEUSA, 2007), pp. 425\u2013428."},{"key":"159_CR9","doi-asserted-by":"crossref","first-page":"1832","DOI":"10.21437\/Interspeech.2012-498","volume-title":"Proceedings of Interspeech","author":"B. Zhang","year":"2012","unstructured":"B. Zhang, R. Schwartz, S. Tsakalidis, L. Nguyen, S. Matsoukas, in Proceedings of Interspeech. White listing and score normalization for keyword spotting of noisy speech (ISCAFrance, 2012), pp. 1832\u20131835."},{"key":"159_CR10","first-page":"15","volume-title":"Proceedings 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 Proceedings of Interspeech. Strategies for high accuracy keyword detection in noisy channels (ISCAFrance, 2013), pp. 15\u201319."},{"key":"159_CR11","first-page":"959","volume-title":"Proceedings 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 Proceedings of Interspeech. Progress in the BBN keyword search system for the DARPA RATS program (ISCAFrance, 2014), pp. 959\u2013963."},{"key":"159_CR12","first-page":"7143","volume-title":"Proceedings 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 Proceedings of ICASSP. Feature fusion for high-accuracy keyword spotting (IEEEUSA, 2014), pp. 7143\u20137147."},{"key":"159_CR13","doi-asserted-by":"publisher","first-page":"760","DOI":"10.21437\/Interspeech.2016-1485","volume-title":"Proceedings of Interspeech","author":"S. Panchapagesan","year":"2016","unstructured":"S. Panchapagesan, M. Sun, A. Khare, S. Matsoukas, A. Mandal, B. Hoffmeister, S. Vitaladevuni, in Proceedings of Interspeech. Multi-task learning and weighted cross-entropy for DNN-based keyword spotting (ISCAFrance, 2016), pp. 760\u2013764."},{"key":"159_CR14","first-page":"615","volume-title":"Proceedings of ACM SIGIR","author":"J. Mamou","year":"2007","unstructured":"J. Mamou, B. Ramabhadran, O. Siohan, in Proceedings of ACM SIGIR. Vocabulary independent spoken term detection (ACMUSA, 2007), pp. 615\u2013622."},{"key":"159_CR15","doi-asserted-by":"crossref","first-page":"697","DOI":"10.21437\/Interspeech.2010-263","volume-title":"Proceedings of Interspeech","author":"D. Schneider","year":"2010","unstructured":"D. Schneider, T. Mertens, M. Larson, J. Kohler, in Proceedings of Interspeech. Contextual verification for open vocabulary spoken term detection (ISCAFrance, 2010), pp. 697\u2013700."},{"key":"159_CR16","doi-asserted-by":"crossref","first-page":"1269","DOI":"10.21437\/Interspeech.2010-399","volume-title":"Proceedings of Interspeech","author":"C. Parada","year":"2010","unstructured":"C. Parada, A. Sethy, M. Dredze, F. Jelinek, in Proceedings of Interspeech. A spoken term detection framework for recovering out-of-vocabulary words using the web (ISCAFrance, 2010), pp. 1269\u20131272."},{"key":"159_CR17","first-page":"42","volume-title":"Proceedings 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 Proceedings of Speech Search Workshop at SIGIR. Hybrid word-subword decoding for spoken term detection (ACMUSA, 2008), pp. 42\u201348."},{"key":"159_CR18","first-page":"2474","volume-title":"Proceedings of Interspeech","author":"Y. Wang","year":"2014","unstructured":"Y. Wang, F. Metze, in Proceedings of Interspeech. An in-depth comparison of keyword specific thresholding and sum-to-one score normalization (ISCAFrance, 2014), pp. 2474\u20132478."},{"key":"159_CR19","first-page":"5331","volume-title":"Proceedings of ICASSP","author":"L. Mangu","year":"2015","unstructured":"L. Mangu, G. Saon, M. Picheny, B. Kingsbury, in Proceedings of ICASSP. Order-free spoken term detection (IEEEUSA, 2015), pp. 5331\u20135335."},{"key":"159_CR20","first-page":"721","volume-title":"Proceedings of MediaEval","author":"A. Buzo","year":"2014","unstructured":"A. Buzo, H. Cucu, C. Burileanu, in Proceedings of MediaEval. SpeeD@MediaEval 2014: spoken term detection with robust multilingual phone recognition (CEURGermany, 2014), pp. 721\u2013722."},{"key":"159_CR21","first-page":"200","volume-title":"Proceedings of NTCIR-12","author":"R. Konno","year":"2016","unstructured":"R. Konno, K. Ouchi, M. Obara, Y. Shimizu, T. Chiba, T. Hirota, Y. Itoh, in Proceedings 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":"159_CR22","first-page":"791","volume-title":"Proceedings of MediaEval","author":"R. Jarina","year":"2013","unstructured":"R. Jarina, M. Kuba, R. Gubka, M. Chmulik, M. Paralic, in Proceedings of MediaEval. UNIZA system for the spoken web search task at MediaEval 2013 (CEURGermany, 2013), pp. 791\u2013792."},{"key":"159_CR23","volume-title":"Proceedings of ICME","author":"X. Anguera","year":"2013","unstructured":"X. Anguera, M. Ferrarons, in Proceedings of ICME. Memory efficient subsequence DTW for query-by-example spoken term detection (IEEEUSA, 2013)."},{"key":"159_CR24","doi-asserted-by":"crossref","first-page":"2191","DOI":"10.21437\/Interspeech.2008-573","volume-title":"Proceedings of Interspeech","author":"H. Lin","year":"2008","unstructured":"H. Lin, A. Stupakov, J. Bilmes, in Proceedings of Interspeech. Spoken keyword spotting via multi-lattice alignment (ISCAFrance, 2008), pp. 2191\u20132194."},{"key":"159_CR25","doi-asserted-by":"crossref","first-page":"693","DOI":"10.21437\/Interspeech.2010-262","volume-title":"Proceedings of Interspeech","author":"C. Chan","year":"2010","unstructured":"C. Chan, L. Lee, in Proceedings of Interspeech. Unsupervised spoken-term detection with spoken queries using segment-based dynamic time warping (ISCAFrance, 2010), pp. 693\u2013696."},{"key":"159_CR26","doi-asserted-by":"crossref","first-page":"2106","DOI":"10.21437\/Interspeech.2008-546","volume-title":"Proceedings of Interspeech","author":"J. Mamou","year":"2008","unstructured":"J. Mamou, B. Ramabhadran, in Proceedings of Interspeech. Phonetic query expansion for spoken document retrieval (ISCAFrance, 2008), pp. 2106\u20132109."},{"key":"159_CR27","first-page":"3957","volume-title":"Proceedings of ICASSP","author":"D. Can","year":"2009","unstructured":"D. Can, E. Cooper, A. Sethy, C. White, B. Ramabhadran, M. Saraclar, in Proceedings of ICASSP. Effect of pronunciations on OOV queries in spoken term detection (IEEEUSA, 2009), pp. 3957\u20133960."},{"key":"159_CR28","first-page":"5280","volume-title":"Proceedings of ICASSP","author":"A. Rosenberg","year":"2017","unstructured":"A. Rosenberg, K. Audhkhasi, A. Sethy, B. Ramabhadran, M. Picheny, in Proceedings of ICASSP. End-to-end speech recognition and keyword search on low-resource languages (IEEEUSA, 2017), pp. 5280\u20135284."},{"key":"159_CR29","first-page":"4840","volume-title":"Proceedings of ICASSP","author":"K. Audhkhasi","year":"2017","unstructured":"K. Audhkhasi, A. Rosenberg, A. Sethy, B. Ramabhadran, B. Kingsbury, in Proceedings of ICASSP. End-to-end ASR-free keyword search from speech (IEEEUSA, 2017), pp. 4840\u20134844."},{"issue":"8","key":"159_CR30","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.1109\/JSTSP.2017.2759726","volume":"11","author":"K. Audhkhasi","year":"2017","unstructured":"K. Audhkhasi, A. Rosenberg, A. Sethy, B. Ramabhadran, B. Kingsbury, End-to-end ASR-free keyword search from speech. IEEE J. Sel. Topics Signal Process.11(8), 1351\u20131359 (2017).","journal-title":"IEEE J. Sel. Topics Signal Process."},{"key":"159_CR31","first-page":"45","volume-title":"Proceedings of Workshop on Searching Spontaneous Conversational Speech","author":"J. G. Fiscus","year":"2007","unstructured":"J. G. Fiscus, J. Ajot, J. S. Garofolo, G. Doddingtion, in Proceedings of Workshop on Searching Spontaneous Conversational Speech. Results of the 2006 spoken term detection evaluation (ACMUSA, 2007), pp. 45\u201350."},{"key":"159_CR32","doi-asserted-by":"publisher","first-page":"1913","DOI":"10.21437\/Interspeech.2016-1381","volume-title":"Proceedings of Interspeech","author":"W. Hartmann","year":"2016","unstructured":"W. Hartmann, L. Zhang, K. Barnes, R. Hsiao, S. Tsakalidis, R. Schwartz, in Proceedings of Interspeech. Comparison of multiple system combination techniques for keyword spotting (ISCAFrance, 2016), pp. 1913\u20131917."},{"key":"159_CR33","first-page":"5755","volume-title":"Proceedings of ICASSP","author":"T. Alumae","year":"2017","unstructured":"T. Alumae, D. Karakos, W. Hartmann, R. Hsiao, L. Zhang, L. Nguyen, S. Tsakalidis, R. Schwartz, in Proceedings of ICASSP. The 2016 BBN Georgian telephone speech keyword spotting system (IEEEUSA, 2017), pp. 5755\u20135759."},{"key":"159_CR34","first-page":"1","volume-title":"Proceedings of NIST Spoken Term Detection Workshop (STD 2006)","author":"D. Vergyri","year":"2006","unstructured":"D. Vergyri, A. Stolcke, R. R. Gadde, W. Wang, in Proceedings of NIST Spoken Term Detection Workshop (STD 2006). The SRI 2006 spoken term detection system (NISTUSA, 2006), pp. 1\u201315."},{"key":"159_CR35","first-page":"2393","volume-title":"Proceedings of Interspeech","author":"D. Vergyri","year":"2007","unstructured":"D. Vergyri, I. Shafran, A. Stolcke, R. R. Gadde, M. Akbacak, B. Roark, W. Wang, in Proceedings of Interspeech. The SRI\/OGI 2006 spoken term detection system (ISCAFrance, 2007), pp. 2393\u20132396."},{"key":"159_CR36","first-page":"5240","volume-title":"Proceedings of ICASSP","author":"M. Akbacak","year":"2008","unstructured":"M. Akbacak, D. Vergyri, A. Stolcke, in Proceedings of ICASSP. Open-vocabulary spoken term detection using graphone-based hybrid recognition systems (IEEEUSA, 2008), pp. 5240\u20135243."},{"key":"159_CR37","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/978-3-540-78155-4_21","volume-title":"Machine Learning for Multimodal Interaction","author":"I. Sz\u00f6ke","year":"2008","unstructured":"I. Sz\u00f6ke, M. Faps\u0306o, M. Karafi\u00e1t, L. Burget, F. Gr\u00e9zl, P. Schwarz, O. Glembek, P. Mate\u0306jka, J. Kopeck\u00fd, J. C\u0306ernock\u00fd, in Machine Learning for Multimodal Interaction, 4892. Spoken term detection system based on combination of LVCSR and phonetic search (SpringerGermany, 2008), pp. 237\u2013247."},{"key":"159_CR38","first-page":"273","volume-title":"Proceedings of SLT","author":"I. Sz\u00f6ke","year":"2008","unstructured":"I. Sz\u00f6ke, L. Burget, J. C\u0306ernock\u00fd, M. Faps\u0306o, in Proceedings of SLT. Sub-word modeling of out of vocabulary words in spoken term detection (IEEEUSA, 2008), pp. 273\u2013276."},{"key":"159_CR39","first-page":"4345","volume-title":"Proceedings of ICASSP","author":"S. Meng","year":"2008","unstructured":"S. Meng, P. Yu, J. Liu, F. Seide, in Proceedings of ICASSP. Fusing multiple systems into a compact lattice index for Chinese spoken term detection (IEEEUSA, 2008), pp. 4345\u20134348."},{"issue":"1","key":"159_CR40","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1109\/TASL.2006.872615","volume":"15","author":"K. Thambiratmann","year":"2007","unstructured":"K. Thambiratmann, S. Sridharan, Rapid yet accurate speech indexing using dynamic match lattice spotting. IEEE Trans. Audio, Speech, Lang. Process.15(1), 346\u2013357 (2007).","journal-title":"IEEE Trans. Audio, Speech, Lang. Process."},{"key":"159_CR41","first-page":"5298","volume-title":"Proceedings of ICASSP","author":"R. Wallace","year":"2010","unstructured":"R. Wallace, R. Vogt, B. Baker, S. Sridharan, in Proceedings of ICASSP. Optimising figure of merit for phonetic spoken term detection (IEEEUSA, 2010), pp. 5298\u20135301."},{"key":"159_CR42","doi-asserted-by":"crossref","first-page":"1676","DOI":"10.21437\/Interspeech.2010-483","volume-title":"Proceedings of Interspeech","author":"A. Jansen","year":"2010","unstructured":"A. Jansen, K. Church, H. Hermansky, in Proceedings of Interspeech. Towards spoken term discovery at scale with zero resources (ISCAFrance, 2010), pp. 1676\u20131679."},{"key":"159_CR43","first-page":"5286","volume-title":"Proceedings of ICASSP","author":"C. Parada","year":"2010","unstructured":"C. Parada, A. Sethy, B. Ramabhadran, in Proceedings of ICASSP. Balancing false alarms and hits in spoken term detection (IEEEUSA, 2010), pp. 5286\u20135289."},{"key":"159_CR44","doi-asserted-by":"publisher","first-page":"3597","DOI":"10.21437\/Interspeech.2017-601","volume-title":"Proceedings of Interspeech","author":"J. Trmal","year":"2017","unstructured":"J. Trmal, M. Wiesner, V. Peddinti, X. Zhang, P. Ghahremani, Y. Wang, V. Manohar, H. Xu, D. Povey, S. Khudanpur, in Proceedings of Interspeech. The Kaldi OpenKWS system: i low resource keyword search (ISCAFrance, 2017), pp. 3597\u20133601."},{"key":"159_CR45","doi-asserted-by":"crossref","first-page":"693","DOI":"10.21437\/Interspeech.2010-262","volume-title":"Proceedings of Interspeech","author":"C. -A. Chan","year":"2010","unstructured":"C. -A. Chan, L. -S. Lee, in Proceedings of Interspeech. Unsupervised spoken-term detection with spoken queries using segment-based dynamic time warping (ISCAFrance, 2010), pp. 693\u2013696."},{"key":"159_CR46","doi-asserted-by":"crossref","first-page":"1672","DOI":"10.21437\/Interspeech.2010-482","volume-title":"Proceedings of Interspeech","author":"C. -P. Chen","year":"2010","unstructured":"C. -P. Chen, H. -Y. Lee, C. -F. Yeh, L. -S. Lee, in Proceedings of Interspeech. Improved spoken term detection by feature space pseudo-relevance feedback (ISCAFrance, 2010), pp. 1672\u20131675."},{"key":"159_CR47","doi-asserted-by":"crossref","first-page":"206","DOI":"10.21437\/Interspeech.2010-86","volume-title":"Proceedings of Interspeech","author":"P. Motlicek","year":"2010","unstructured":"P. Motlicek, F. Valente, P. Garner, in Proceedings of Interspeech. English spoken term detection in multilingual recordings (ISCAFrance, 2010), pp. 206\u2013209."},{"key":"159_CR48","first-page":"1","volume-title":"Proceedings of NIST Spoken Term Detection Evaluation Workshop (STD\u201906)","author":"I. Sz\u00f6ke","year":"2006","unstructured":"I. Sz\u00f6ke, M. Faps\u0306o, M. Karafi\u00e1t, L. Burget, F. Gr\u00e9zl, P. Schwarz, O. Glembek, P. Mate\u0306jka, S. Kont\u00e1r, J. C\u0306ernock\u00fd, in Proceedings of NIST Spoken Term Detection Evaluation Workshop (STD\u201906). BUT system for NIST STD 2006 - English (NISTUSA, 2006), pp. 1\u201315."},{"key":"159_CR49","first-page":"314","volume-title":"Proceedings 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 Proceedings of Interspeech. Rapid and accurate spoken term detection (ISCAFrance, 2007), pp. 314\u2013317."},{"key":"159_CR50","doi-asserted-by":"crossref","first-page":"2430","DOI":"10.21437\/Interspeech.2012-636","volume-title":"Proceedings of Interspeech","author":"H. Li","year":"2012","unstructured":"H. Li, J. Han, T. Zheng, G. Zheng, in Proceedings of Interspeech. A novel confidence measure based on context consistency for spoken term detection (ISCAFrance, 2012), pp. 2430\u20132433."},{"key":"159_CR51","first-page":"2247","volume-title":"Proceedings of Interspeech","author":"J. Chiu","year":"2013","unstructured":"J. Chiu, A. Rudnicky, in Proceedings of Interspeech. Using conversational word bursts in spoken term detection (ISCAFrance, 2013), pp. 2247\u20132251."},{"key":"159_CR52","first-page":"5650","volume-title":"Proceedings of ICASSP","author":"C. Ni","year":"2017","unstructured":"C. Ni, C. -C. Leung, L. Wang, N. F. Chen, B. Ma, in Proceedings of ICASSP. Efficient methods to train multilingual bottleneck feature extractors for low resource keyword search (IEEEUSA, 2017), pp. 5650\u20135654."},{"key":"159_CR53","doi-asserted-by":"publisher","first-page":"770","DOI":"10.21437\/Interspeech.2016-642","volume-title":"Proceedings of Interspeech","author":"Z. Meng","year":"2016","unstructured":"Z. Meng, B. -H. Juang, in Proceedings of Interspeech. Non-uniform boosted MCE training of deep neural networks for keyword spotting (ISCAFrance, 2016), pp. 770\u2013774."},{"key":"159_CR54","doi-asserted-by":"publisher","first-page":"3547","DOI":"10.21437\/Interspeech.2017-583","volume-title":"Proceedings of Interspeech","author":"Z. Meng","year":"2017","unstructured":"Z. Meng, B. -H. Juang, in Proceedings of Interspeech. Non-uniform MCE training of deep long short-term memory recurrent neural networks for keyword spotting (ISCAFrance, 2017), pp. 3547\u20133551."},{"key":"159_CR55","first-page":"3685","volume-title":"Proceedings of Interspeech","author":"S. -w. Lee","year":"2015","unstructured":"S. -w. Lee, K. Tanaka, Y. Itoh, in Proceedings of Interspeech. Combination of diverse subword units in spoken term detection (ISCAFrance, 2015), pp. 3685\u20133289."},{"key":"159_CR56","first-page":"5780","volume-title":"Proceedings of ICASSP","author":"C. van Heerden","year":"2017","unstructured":"C. van Heerden, D. Karakos, K. Narasimhan, M. Davel, R. Schwartz, in Proceedings of ICASSP. Constructing sub-word units for spoken term detection (IEEEUSA, 2017), pp. 5780\u20135784."},{"key":"159_CR57","doi-asserted-by":"publisher","first-page":"2879","DOI":"10.21437\/Interspeech.2017-634","volume-title":"Proceedings of Interspeech","author":"D. Kaneko","year":"2017","unstructured":"D. Kaneko, R. Konno, K. Kojima, K. Tanaka, S. -w. Lee, Y. Itoh, in Proceedings of Interspeech. Constructing acoustic distances between subwords and states obtained from a deep neural network for spoken term detection (ISCAFrance, 2017), pp. 2879\u20132883."},{"key":"159_CR58","first-page":"114","volume-title":"Proceedings of International Symposium on Information and Communication Technology","author":"V. T. Pham","year":"2017","unstructured":"V. T. Pham, H. Xu, X. Xiao, N. F. Chen, E. S. Chng, in Proceedings of International Symposium on Information and Communication Technology. Pruning strategies for partial search in spoken term detection (ACMUSA, 2017), pp. 114\u2013119."},{"issue":"2","key":"159_CR59","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1016\/j.specom.2012.08.006","volume":"55","author":"M. Wollmer","year":"2013","unstructured":"M. Wollmer, B. Schuller, G. Rigoll, Keyword spotting exploiting long short-term memory. Speech Comm.55(2), 252\u2013265 (2013).","journal-title":"Speech Comm."},{"issue":"5","key":"159_CR60","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). Elsevier, Amsterdam.","journal-title":"Comput. Speech Lang."},{"key":"159_CR61","doi-asserted-by":"publisher","first-page":"938","DOI":"10.21437\/Interspeech.2016-753","volume-title":"Proceedings of Interspeech","author":"Y. Zhuang","year":"2016","unstructured":"Y. Zhuang, X. Chang, Y. Qian, K. Yu, in Proceedings of Interspeech. Unrestricted vocabulary keyword spotting using LSTM-CTC (ISCAFrance, 2016), pp. 938\u2013942."},{"key":"159_CR62","doi-asserted-by":"publisher","first-page":"112","DOI":"10.21437\/Interspeech.2018-1016","volume-title":"Proceedings of Interspeech","author":"L. Pandey","year":"2018","unstructured":"L. Pandey, K. Nathwani, in Proceedings of Interspeech. LSTM based attentive fusion of spectral and prosodic information for keyword spotting in hindi language (ISCAFrance, 2018), pp. 112\u2013116."},{"key":"159_CR63","first-page":"5785","volume-title":"Proceedings of ICASSP","author":"R. Lileikyte","year":"2017","unstructured":"R. Lileikyte, T. Fraga-Silva, L. Lamel, J. -L. Gauvain, A. Laurent, G. Huang, in Proceedings of ICASSP. Effective keyword search for low-resourced conversational speech (IEEEUSA, 2017), pp. 5785\u20135789."},{"key":"159_CR64","first-page":"5244","volume-title":"Proceedings of ICASSP","author":"S. Parlak","year":"2008","unstructured":"S. Parlak, M. Sara\u00e7lar, in Proceedings of ICASSP. Spoken term detection for Turkish broadcast news (IEEEUSA, 2008), pp. 5244\u20135247."},{"key":"159_CR65","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.specom.2018.09.004","volume":"104","author":"V. T. Pham","year":"2018","unstructured":"V. T. Pham, H. Xu, X. Xiao, N. F. Chen, E. S. Chng, Re-ranking spoken term detection with acoustic exemplars of keywords. Speech Comm.104:, 12\u201323 (2018).","journal-title":"Speech Comm."},{"key":"159_CR66","first-page":"5770","volume-title":"Proceedings of ICASSP","author":"A. Ragni","year":"2017","unstructured":"A. Ragni, D. Saunders, P. Zahemszky, J. Vasilakes, M. J. F. Gales, K. M. Knill, in Proceedings of ICASSP. Morph-to-word transduction for accurate and efficient automatic speech recognition and keyword search (IEEEUSA, 2017), pp. 5770\u20135774."},{"key":"159_CR67","first-page":"5775","volume-title":"Proceedings of ICASSP","author":"X. Chen","year":"2017","unstructured":"X. Chen, A. Ragnil, J. Vasilakes, X. Liu, K. Knilll, M. J.. F. Gales, in Proceedings of ICASSP. Recurrent neural network language models for keyword search (IEEEUSA, 2017), pp. 5775\u20135779."},{"key":"159_CR68","first-page":"2774","volume-title":"Proceedings of Interspeech","author":"D. Xu","year":"2014","unstructured":"D. Xu, F. Metze, in Proceedings of Interspeech. Word-based probabilistic phonetic retrieval for low-resource spoken term detection (ISCAFrance, 2014), pp. 2774\u20132778."},{"key":"159_CR69","doi-asserted-by":"publisher","first-page":"2934","DOI":"10.21437\/Interspeech.2017-1087","volume-title":"Proceedings of Interspeech","author":"J. Svec","year":"2017","unstructured":"J. Svec, J. V. Psutka, L. Smidl, J. Trmal, in Proceedings of Interspeech. A relevance score estimation for spoken term detection based on RNN-generated pronunciation embeddings (ISCAFrance, 2017), pp. 2934\u20132938."},{"key":"159_CR70","doi-asserted-by":"publisher","first-page":"3602","DOI":"10.21437\/Interspeech.2017-1212","volume-title":"Proceedings of Interspeech","author":"Y. Khokhlov","year":"2017","unstructured":"Y. Khokhlov, I. Medennikov, A. Romanenko, V. Mendelev, M. Korenevsky, A. Prudnikov, N. Tomashenko, A. Zatvornitsky, in Proceedings of Interspeech. The STC keyword search system for OpenKWS 2016 evaluation (ISCAFrance, 2017), pp. 3602\u20133606."},{"key":"159_CR71","unstructured":"S. Young, G. Evermann, M. Gales, T. Hain, D. Kershaw, X. Liu, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, P. Woodland, The HTK Book (v3.4). Engineering Department, Cambridge University (2009)."},{"issue":"1","key":"159_CR72","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1109\/29.45616","volume":"38","author":"K. -F. Lee","year":"1990","unstructured":"K. -F. Lee, H. -W. Hon, R. Reddy, An overview of the SPHINX speech recognition system. IEEE Trans. Acoust., Speech, Signal Process.38(1), 35\u201345 (1990).","journal-title":"IEEE Trans. Acoust., Speech, Signal Process."},{"key":"159_CR73","volume-title":"Proceedings 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 Proceedings of ASRU. The KALDI speech recognition toolkit (IEEEUSA, 2011)."},{"key":"159_CR74","first-page":"8560","volume-title":"Proceedings of ICASSP","author":"G. Chen","year":"2013","unstructured":"G. Chen, S. Khudanpur, D. Povey, J. Trmal, D. Yarowsky, O. Yilmaz, in Proceedings of ICASSP. Quantifying the value of pronunciation lexicons for keyword search in low resource languages (IEEEUSA, 2013), pp. 8560\u20138564."},{"key":"159_CR75","first-page":"430","volume-title":"Proceedings 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 Proceedings of SLT. System and keyword dependent fusion for spoken term detection (IEEEUSA, 2014), pp. 430\u2013435."},{"key":"159_CR76","first-page":"416","volume-title":"Proceedings of ASRU","author":"G. Chen","year":"2013","unstructured":"G. Chen, O. Yilmaz, J. Trmal, D. Povey, S. Khudanpur, in Proceedings of ASRU. Using proxies for OOV keywords in the keyword search task (IEEEUSA, 2013), pp. 416\u2013421."},{"key":"159_CR77","first-page":"1","volume":"1","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. 1:, 1\u201310 (2011).","journal-title":"EURASIP J. Audio, Speech, Music Process"},{"key":"159_CR78","first-page":"1","volume":"19","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.19:, 1\u20139 (2012).","journal-title":"EURASIP J. Audio, Speech, Music Process."},{"key":"159_CR79","doi-asserted-by":"crossref","first-page":"1529","DOI":"10.21437\/Interspeech.2011-322","volume-title":"Proceedings 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 Proceedings of Interspeech. The Albayzin 2010 Language Recognition Evaluation (ISCAFrance, 2011), pp. 1529\u20131532."},{"issue":"21","key":"159_CR80","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":"159_CR81","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":"159_CR82","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":"159_CR83","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":"159_CR84","first-page":"317","volume-title":"Proceedings of FALA","author":"F. M\u00e9ndez","year":"2010","unstructured":"F. M\u00e9ndez, L. Doc\u00edo, M. Arza, F. Campillo, in Proceedings of FALA. The Albayzin 2010 text-to-speech evaluation (ISCAFrance, 2010), pp. 317\u2013340."},{"issue":"22","key":"159_CR85","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":"159_CR86","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. P. ao, 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":"159_CR87","volume-title":"Proceedings 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 Proceedings of Eurospeech. Multilingual speech recognition: the 1996 Byblos callhome system (ISCAFrance, 1997)."},{"key":"159_CR88","first-page":"156","volume-title":"Proceedings of MICAI","author":"H. Cuayahuitl","year":"2002","unstructured":"H. Cuayahuitl, B. Serridge, in Proceedings of MICAI. Out-of-vocabulary word modeling and rejection for spanish keyword spotting systems (SpringerGermany, 2002), pp. 156\u2013165."},{"key":"159_CR89","doi-asserted-by":"crossref","first-page":"3141","DOI":"10.21437\/Eurospeech.2003-785","volume-title":"Proceedings of Eurospeech","author":"M. Killer","year":"2003","unstructured":"M. Killer, S. Stuker, T. Schultz, in Proceedings of Eurospeech. Grapheme based speech recognition (ISCAFrance, 2003), pp. 3141\u20133144."},{"key":"159_CR90","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, Spain, 2009)."},{"key":"159_CR91","first-page":"4334","volume-title":"Proceedings 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 Proceedings of ICASSP. Multilingual acoustic modeling for speech recognition based on subspace gaussian mixture models (IEEEUSA, 2010), pp. 4334\u20134337."},{"issue":"5","key":"159_CR92","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":"159_CR93","first-page":"1747","volume-title":"Proceedings of Interspeech","author":"J. Li","year":"2014","unstructured":"J. Li, X. Wang, B. Xu, in Proceedings of Interspeech. An empirical study of multilingual and low-resource spoken term detection using deep neural networks (ISCAFrance, 2014), pp. 1747\u20131751."},{"key":"159_CR94","volume-title":"Student Test","author":"M. Hazewinkel","year":"1994","unstructured":"M. Hazewinkel, Student Test (Kluwer Academic, Denmark, 1994)."},{"key":"159_CR95","volume-title":"The Spoken Term Detection (STD) 2006 Evaluation Plan","author":"NIST","year":"2006","unstructured":"NIST, The Spoken Term Detection (STD) 2006 Evaluation Plan, 10th edn. (National Institute of Standards and Technology (NIST), Gaithersburg, MD, USA, 2006). http:\/\/www.nist.gov\/speech\/tests\/std ."},{"key":"159_CR96","doi-asserted-by":"crossref","first-page":"1895","DOI":"10.21437\/Eurospeech.1997-504","volume-title":"Proceedings of Eurospeech","author":"A. Martin","year":"1997","unstructured":"A. Martin, G. Doddington, T. Kamm, M. Ordowski, M. Przybocki, in Proceedings of Eurospeech. The DET curve in assessment of detection task performance (ISCAFrance, 1997), pp. 1895\u20131898."},{"key":"159_CR97","volume-title":"Evaluation Toolkit (STDEval) Software","author":"NIST","year":"1996","unstructured":"NIST, Evaluation Toolkit (STDEval) Software (National Institute of Standards and Technology (NIST), Gaithersburg, MD, USA, 1996). http:\/\/www.itl.nist.gov\/iad\/mig\/tests\/std\/tools ."},{"key":"159_CR98","unstructured":"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 11 Aug 2019."},{"key":"159_CR99","volume-title":"RTVE2018 Database Description","author":"E. Lleida","year":"2018","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, Spain, 2018). http:\/\/catedrartve.unizar.es\/reto2018\/RTVE2018DB.pdf ."},{"key":"159_CR100","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":"159_CR101","doi-asserted-by":"publisher","first-page":"745","DOI":"10.21437\/Interspeech.2016-606","volume-title":"Proceedings of Interspeech","author":"Z. Lv","year":"2016","unstructured":"Z. Lv, M. Cai, W. -Q. Zhang, J. Liu, in Proceedings of Interspeech. A novel discriminative score calibration method for keyword search (ISCAFrance, 2016), pp. 745\u2013749."},{"key":"159_CR102","doi-asserted-by":"publisher","first-page":"1913","DOI":"10.21437\/Interspeech.2016-1381","volume-title":"Proceedings of Interspeech","author":"W. Hartmann","year":"2016","unstructured":"W. Hartmann, L. Zhang, K. Barnes, R. Hsiao, S. Tsakalidis, R. Schwartz, in Proceedings of Interspeech. Comparison of multiple system combination techniques for keyword spotting (ISCAFrance, 2016), pp. 1913\u20131917."},{"key":"159_CR103","first-page":"6040","volume-title":"Proceedings of ICASSP","author":"N. F. Chen","year":"2016","unstructured":"N. F. Chen, V. T. Pharri, H. Xu, X. Xiao, V. H. Do, C. Ni, I. -F. Chen, S. Sivadas, C. -H. Lee, E. S. Chng, B. Ma, H. Li, in Proceedings of ICASSP. Exemplar-inspired strategies for low-resource spoken keyword search in Swahili (IEEEUSA, 2016), pp. 6040\u20136044."},{"key":"159_CR104","first-page":"6015","volume-title":"Proceedings of ICASSP","author":"C. Ni","year":"2016","unstructured":"C. Ni, C. -C. Leung, L. Wang, H. Liu, F. Rao, L. Lu, N. F. Chen, B. Ma, H. Li, in Proceedings of ICASSP. Cross-lingual deep neural network based submodular unbiased data selection for low-resource keyword search (IEEEUSA, 2016), pp. 6015\u20136019."},{"key":"159_CR105","first-page":"215","volume-title":"Proceedings of ASRU","author":"M. Cai","year":"2015","unstructured":"M. Cai, Z. Lv, C. Lu, J. Kang, L. Hui, Z. Zhang, J. Liu, in Proceedings of ASRU. High-performance swahili keyword search with very limited language pack: The THUEE system for the OpenKWS15 evaluation (IEEEUSA, 2015), pp. 215\u2013222."},{"key":"159_CR106","first-page":"5366","volume-title":"Proceedings of ICASSP","author":"N. F. Chen","year":"2015","unstructured":"N. F. Chen, C. Ni, I. -F. Chen, S. Sivadas, V. T. Pham, H. Xu, X. Xiao, T. S. Lau, S. J. Leow, B. P. Lim, C. -C. Leung, L. Wang, C. -H. Lee, A. Goh, E. S. Chng, B. Ma, H. Li, in Proceedings of ICASSP. Low-resource keyword search strategies for Tamil (IEEEUSA, 2015), pp. 5366\u20135370."},{"key":"159_CR107","first-page":"5765","volume-title":"Proceedings of ICASSP","author":"W. Hartmann","year":"2017","unstructured":"W. Hartmann, D. Karakos, R. Hsiao, L. Zhang, T. Alumae, S. Tsakalidis, R. Schwartz, in Proceedings of ICASSP. Analysis of keyword spotting performance across IARPA babel languages (IEEEUSA, 2017), pp. 5765\u20135769."},{"key":"159_CR108","volume-title":"OpenKWS13 Keyword Search Evaluation Plan","author":"NIST","year":"2013","unstructured":"NIST, OpenKWS13 Keyword Search Evaluation Plan (National Institute of Standards and Technology (NIST), Gaithersburg, MD, USA, 2013). https:\/\/www.nist.gov\/sites\/default\/files\/documents\/itl\/iad\/mig\/OpenKWS13-evalplan-v4.pdf ."},{"key":"159_CR109","volume-title":"Draft KWS14 Keyword Search Evaluation Plan","author":"NIST","year":"2013","unstructured":"NIST, Draft KWS14 Keyword Search Evaluation Plan (National Institute of Standards and Technology (NIST), Gaithersburg, MD, USA, 2013). https:\/\/www.nist.gov\/sites\/default\/files\/documents\/itl\/iad\/mig\/KWS14-evalplan-v11.pdf ."},{"key":"159_CR110","volume-title":"KWS15 Keyword Search Evaluation Plan","author":"NIST","year":"2015","unstructured":"NIST, KWS15 Keyword Search Evaluation Plan (National Institute of Standards and Technology (NIST), Gaithersburg, MD, USA, 2015). https:\/\/www.nist.gov\/sites\/default\/files\/documents\/itl\/iad\/mig\/KWS15-evalplan-v05.pdf ."},{"key":"159_CR111","volume-title":"Draft KWS16 Keyword Search Evaluation Plan","author":"NIST","year":"2016","unstructured":"NIST, Draft KWS16 Keyword Search Evaluation Plan (National Institute of Standards and Technology (NIST), Gaithersburg, MD, USA, 2016). https:\/\/www.nist.gov\/sites\/default\/files\/documents\/itl\/iad\/mig\/KWS16-evalplan-v04.pdf ."},{"key":"159_CR112","first-page":"1","volume-title":"Proceedings of NTCIR-9","author":"T. Akiba","year":"2011","unstructured":"T. Akiba, H. Nishizaki, K. Aikawa, T. Kawahara, T. Matsui, in Proceedings of NTCIR-9. Overview of the IR for Spoken Documents Task in NTCIR-9 Workshop (Japan Society for Promotion of ScienceJapan, 2011), pp. 1\u201313."},{"key":"159_CR113","first-page":"1","volume-title":"Proceedings of NTCIR-10","author":"T. Akiba","year":"2013","unstructured":"T. Akiba, H. Nishizaki, K. Aikawa, X. Hu, Y. Itoh, T. Kawahara, S. Nakagawa, H. Nanjo, Y. Yamashita, in Proceedings of NTCIR-10. Overview of the NTCIR-10 SpokenDoc-2 task (Japan Society for Promotion of ScienceJapan, 2013), pp. 1\u201315."},{"key":"159_CR114","first-page":"1","volume-title":"Proceedings of NTCIR-11","author":"T. Akiba","year":"2014","unstructured":"T. Akiba, H. Nishizaki, H. Nanjo, G. J. F. Jones, in Proceedings of NTCIR-11. Overview of the NTCIR-11 SpokenQuery&Doc Task (Japan Society for Promotion of ScienceJapan, 2014), pp. 1\u201315."},{"key":"159_CR115","first-page":"1","volume-title":"Proceedings of NTCIR-12","author":"T. Akiba","year":"2016","unstructured":"T. Akiba, H. Nishizaki, H. Nanjo, G. J. F. Jones, in Proceedings of NTCIR-12. Overview of the NTCIR-12 SpokenQuery&Doc-2 Task (Japan Society for Promotion of ScienceJapan, 2016), pp. 1\u201313."},{"key":"159_CR116","first-page":"2345","volume-title":"Proceedings of Interspeech","author":"K. Vesely","year":"2013","unstructured":"K. Vesely, A. Ghoshal, L. Burget, D. Povey, in Proceedings of Interspeech. Sequence-discriminative training of deep neural networks (ISCAFrance, 2013), pp. 2345\u20132349."},{"key":"159_CR117","first-page":"2494","volume-title":"Proceedings of ICASSP","author":"P. Ghahremani","year":"2014","unstructured":"P. Ghahremani, B. BabaAli, D. Povey, K. Riedhammer, J. Trmal, S. Khudanpur, in Proceedings of ICASSP. A pitch extraction algorithm tuned for automatic speech recognition (IEEEUSA, 2014), pp. 2494\u20132498."},{"key":"159_CR118","first-page":"4213","volume-title":"Proceedings of ICASSP","author":"D. Povey","year":"2012","unstructured":"D. Povey, M. Hannemann, G. Boulianne, L. Burget, A. Ghoshal, M. Janda, M. Karafiat, S. Kombrink, P. Motlicek, Y. Qian, K. Riedhammer, K. Vesely, N. T. Vu, in Proceedings of ICASSP. Generating exact lattices in the WFST framework (IEEEUSA, 2012), pp. 4213\u20134216."},{"key":"159_CR119","volume-title":"Proceedings of LREC","author":"C. Garcia-Mateo","year":"2004","unstructured":"C. Garcia-Mateo, J. Dieguez-Tirado, L. Docio-Fernandez, A. Cardenal-Lopez, in Proceedings of LREC. Transcrigal: A bilingual system for automatic indexing of broadcast news (ELRABelgium, 2004)."},{"key":"159_CR120","first-page":"224","volume-title":"Proceedings of Iberspeech","author":"A. Moreno","year":"2004","unstructured":"A. Moreno, L. Campillos, in Proceedings of Iberspeech. MAVIR: a corpus of spontaneous formal speech in spanish and english (ISCAFrance, 2004), pp. 224\u2013230."},{"key":"159_CR121","first-page":"901","volume-title":"Proceedings of Interspeech","author":"A. Stolcke","year":"2002","unstructured":"A. Stolcke, in Proceedings of Interspeech. SRILM - an extensible language modeling toolkit (ISCAFrance, 2002), pp. 901\u2013904."},{"key":"159_CR122","first-page":"308","volume-title":"Proceedings of Iberspeech","author":"E. Rodr\u00edguez-Banga","year":"2012","unstructured":"E. Rodr\u00edguez-Banga, C. Garcia-Mateo, F. M\u00e9ndez-Paz\u00f3, M. Gonz\u00e1lez-Gonz\u00e1lez, C. Magari\u00f1os, in Proceedings of Iberspeech. Cotov\u00eda: an open source TTS for galician and spanish (ISCAFrance, 2012), pp. 308\u2013315."},{"issue":"8","key":"159_CR123","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":"159_CR124","first-page":"680","volume-title":"Proceedings of ECIR","author":"J. Parapar","year":"2009","unstructured":"J. Parapar, A. Freire, A. Barreiro, in Proceedings of ECIR. Revisiting n-gram based models for retrieval in degraded large collections (SpringerGermany, 2009), pp. 680\u2013684."},{"issue":"1","key":"159_CR125","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."},{"key":"159_CR126","first-page":"275","volume-title":"Proceedings of ACM SIGIR","author":"J. Ponte","year":"1998","unstructured":"J. Ponte, W. Croft, in Proceedings of ACM SIGIR. A language modeling approach to information retrieval (ACMUSA, 1998), pp. 275\u2013281."},{"key":"159_CR127","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, Cambridge, 2008)."},{"key":"159_CR128","first-page":"20","volume-title":"Proceedings of Interspeech","author":"A. Abad","year":"2013","unstructured":"A. Abad, L. J. Rodr\u00edguez-Fuentes, M. Pe\u00f1agarikano, A. Varona, G. Bordel, in Proceedings of Interspeech. On the calibration and fusion of heterogeneous spoken term detection systems (ISCAFrance, 2013), pp. 20\u201324."},{"key":"159_CR129","first-page":"1","volume-title":"Proceedings of IEEE Odyssey 2006: The Speaker and Language Recognition Workshop","author":"N. Brummer","year":"2006","unstructured":"N. Brummer, D. van Leeuwen, in Proceedings of IEEE Odyssey 2006: The Speaker and Language Recognition Workshop. On calibration of language recognition scores (IEEEUSA, 2006), pp. 1\u20138."},{"key":"159_CR130","unstructured":"N. Brummer, E. de Villiers, The BOSARIS toolkit user guide: theory, algorithms and code for binary classifier score processing. Agnitio Labs (2011). https:\/\/sites.google.com\/site\/nikobrummer . Accessed 11 Aug 2019."},{"issue":"2","key":"159_CR131","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1016\/j.csl.2010.06.003","volume":"25","author":"D. Povey","year":"2011","unstructured":"D. Povey, L. Burget, M. Agarwal, P. Akyazi, F. Kai, A. Ghoshal, O. Glembek, N. Goel, M. Karafiat, A. Rastrow, R. C. Rose, P. Schwarz, S. Thomas, The subspace Gaussian mixture model: a structured model for speech recognition. Comput. Speech Lang. 25(2), 404\u2013439 (2011).","journal-title":"Comput. Speech Lang"},{"key":"159_CR132","unstructured":"gTTS (Google Text-to-Speech), Python library and CLI tool to interface with Google Translate\u2019s text-to-speech API. https:\/\/pypi.org\/project\/gTTS\/ . Accessed 11 Aug 2019."},{"key":"159_CR133","unstructured":"NSSpeechSynthesizer, The cocoa interface to speech synthesis in macOS (AppKit Module of PyObjC Bridge). https:\/\/developer.apple.com\/documentation\/appkit\/nsspeechsynthesizer . Accessed 11 Aug 2019."},{"key":"159_CR134","unstructured":"Python Interface to the WebRTC (https:\/\/webrtc.org\/) Voice activity detector (VAD). https:\/\/github.com\/wiseman\/py-webrtcvad . Accessed 11 Aug 2019."},{"key":"159_CR135","doi-asserted-by":"publisher","first-page":"283","DOI":"10.21437\/Odyssey.2018-40","volume-title":"Proceedings 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 Proceedings of Odyssey. BUT\/Phonexia bottleneck feature extractor (IEEEUSA, 2018), pp. 283\u2013287."},{"key":"159_CR136","first-page":"69","volume-title":"Proceedings of LREC","author":"C. Cieri","year":"2004","unstructured":"C. Cieri, D. Miller, K. Walker, in Proceedings of LREC. The Fisher Corpus: a resource for the next generations of speech-to-text (ELRABelgium, 2004), pp. 69\u201371."},{"key":"159_CR137","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 11 Aug 2019."},{"key":"159_CR138","first-page":"7819","volume-title":"Proceedings of ICASSP","author":"L. J. Rodriguez-Fuentes","year":"2014","unstructured":"L. J. Rodriguez-Fuentes, A. Varona, M. Penagarikano, G. Bordel, M. Diez, in Proceedings of ICASSP. High-performance query-by-example spoken term detection on the SWS 2013 evaluation (IEEEUSA, 2014), pp. 7819\u20137823."},{"key":"159_CR139","first-page":"20","volume-title":"Proceedings of Interspeech","author":"A. Abad","year":"2013","unstructured":"A. Abad, L. J. Rodriguez-Fuentes, M. Penagarikano, A. Varona, M. Diez, G. Bordel, in Proceedings of Interspeech. On the calibration and fusion of heterogeneous spoken term detection systems (ISCAFrance, 2013), pp. 20\u201324."}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-019-0159-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13636-019-0159-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-019-0159-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T05:26:44Z","timestamp":1664256404000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13636-019-0159-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,2]]},"references-count":139,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["159"],"URL":"https:\/\/doi.org\/10.1186\/s13636-019-0159-7","relation":{},"ISSN":["1687-4722"],"issn-type":[{"type":"electronic","value":"1687-4722"}],"subject":[],"published":{"date-parts":[[2019,9,2]]},"assertion":[{"value":"7 March 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 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":"16"}}