{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T16:30:18Z","timestamp":1771000218429,"version":"3.50.1"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2013,12,14]],"date-time":"2013-12-14T00:00:00Z","timestamp":1386979200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2014,6]]},"DOI":"10.1007\/s10772-013-9217-1","type":"journal-article","created":{"date-parts":[[2013,12,13]],"date-time":"2013-12-13T07:25:30Z","timestamp":1386919530000},"page":"183-198","source":"Crossref","is-referenced-by-count":28,"title":["Recent developments in spoken term detection: a survey"],"prefix":"10.1007","volume":"17","author":[{"given":"Anupam","family":"Mandal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"K. R.","family":"Prasanna\u00a0Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pabitra","family":"Mitra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,12,14]]},"reference":[{"key":"9217_CR1","volume-title":"HLT-NAACL","author":"C. Allauzen","year":"2004","unstructured":"Allauzen, C., Mohri, M., & Saraclar, M. (2004). General indexation of weighted automata: application to spoken utterance retrieval. In HLT-NAACL, Boston, USA."},{"key":"9217_CR2","doi-asserted-by":"crossref","unstructured":"Avidan, S., & Shamir, A. (2007). Seam carving for content-aware image resizing. ACM Transactions on Graph, 26(3).","DOI":"10.1145\/1276377.1276390"},{"key":"9217_CR3","volume-title":"Proceedings of the 4th conference on human language technology","author":"L. Baghai-Ravary","year":"2009","unstructured":"Baghai-Ravary, L., Kochanski, G., & Coleman, J. (2009). Data-driven approaches to objective evaluation of phoneme alignment systems. In Proceedings of the 4th conference on human language technology, Poznan, Poland."},{"key":"9217_CR4","volume-title":"Proc. int. conf. acoustics, speech and signal processing","author":"S. Barnwal","year":"2012","unstructured":"Barnwal, S., Sahni, K., Singh, R., & Raj, B. (2012). Spectrographic seam patterns for discriminative word spotting. In Proc. int. conf. acoustics, speech and signal processing, Kyoto, Japan."},{"key":"9217_CR5","volume-title":"Proc. int. conf. acoustics, speech and signal processing","author":"Y. D. Benayed","year":"2003","unstructured":"Benayed, Y. D., Fohr, J. H., & Chollet, G. (2003). Confidence measures for keyword spotting using support vector machines. In Proc. int. conf. acoustics, speech and signal processing, Hong Kong."},{"key":"9217_CR6","volume-title":"Proc. int. conf. speech processing","author":"L. Boves","year":"2009","unstructured":"Boves, L., Carlson, R., Hinrichs, E., House, D., Krauwer, S., Lemnitzer, L., Vainio, M., & Wittenburg, P. (2009). Resources for speech research: present and future infrastructure needs. In Proc. int. conf. speech processing, Brighton, UK."},{"key":"9217_CR7","volume-title":"Proc. of British acoustic society meeting","author":"J. Bridle","year":"1973","unstructured":"Bridle, J. (1973). An efficient elastic template method for detecting given key words in running speech. In Proc. of British acoustic society meeting, UK."},{"issue":"8","key":"9217_CR8","doi-asserted-by":"crossref","first-page":"2338","DOI":"10.1109\/TASL.2011.2134087","volume":"19","author":"D. Can","year":"2011","unstructured":"Can, D. (2011). Lattice indexing for spoken term detection. IEEE Transactions on Audio, Speech, and Language Processing, 19(8), 2338\u20132347.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9217_CR9","volume-title":"Proc. int. conf. acoustics, speech and signal processing","author":"P. Can","year":"2009","unstructured":"Can, P., Cooper, E., Sethy, A., White, C., Ramabhadran, B., & Saraclar, M. (2009). Effect of pronunciations on oov queries in spoken term detection. In Proc. int. conf. acoustics, speech and signal processing, Taipei, Taiwan."},{"key":"9217_CR10","volume-title":"Proc. int. conf. speech processing","author":"C. Chan","year":"2010","unstructured":"Chan, C., & Lee, L. (2010). Unsupervised spoken-term detection with spoken queries using segment-based dynamic time warping. In Proc. int. conf. speech processing, Chiba, Japan."},{"key":"9217_CR11","volume-title":"Proc. int. conf. acoustics, speech and signal processing","author":"C. Chan","year":"2011","unstructured":"Chan, C., & Lee, L. (2011). Integrating frame-based and segment-based dynamic time warping for unsupervised spoken term detection with spoken queries. In Proc. int. conf. acoustics, speech and signal processing, Prague."},{"key":"9217_CR12","volume-title":"Annual conference of the association of computational linguistics","author":"C. Chelba","year":"2005","unstructured":"Chelba, C., & Acero, A. (2005). Position specific posterior lattices for indexing speech. In Annual conference of the association of computational linguistics, Ann Arbor, USA."},{"key":"9217_CR13","volume-title":"Proc. int. conf. acoustics, speech and signal processing","author":"S. Deligne","year":"1995","unstructured":"Deligne, S., & Bimbot, F. (1995). Language modeling by variable length sequences. In Proc. int. conf. acoustics, speech and signal processing, Michigan, USA."},{"key":"9217_CR14","volume-title":"ISCA workshop statistical and perceptual audition","author":"T. Ezzat","year":"2008","unstructured":"Ezzat, T., & Poggio, T. (2008). Discriminative word spotting using ordered spectro-temporal patch features. In ISCA workshop statistical and perceptual audition, Brisbane, Australia."},{"key":"9217_CR15","volume-title":"Proc. int. conf. acoustics, speech and signal processing","author":"P. Fousek","year":"2006","unstructured":"Fousek, P., & Hermansky, H. (2006). Towards ASR based on hierarchical posterior-based keyword recognition. In Proc. int. conf. acoustics, speech and signal processing, Toulouse, France."},{"key":"9217_CR16","volume-title":"Proc. int. conf. acoustics, speech and signal processing","author":"A. Garcia","year":"2006","unstructured":"Garcia, A., & Gish, H. (2006). Keyword spotting of arbitrary words using minimal speech resources. In Proc. int. conf. acoustics, speech and signal processing, Toulouse, France."},{"key":"9217_CR17","volume-title":"Ninth text retrieval conference (TREC-9) NIST","author":"J. Garofolo","year":"2000","unstructured":"Garofolo, J., Auzzane, G., & Voorhees, E. (2000). The trec spoken document retrieval track: a success story. In Ninth text retrieval conference (TREC-9) NIST."},{"key":"9217_CR18","volume-title":"Automatic speech and speaker recognition: large margin and kernel methods","author":"D. Grangier","year":"2009","unstructured":"Grangier, D., Keshet, J., & Bengio, S. (2009). Chapter on discriminative keyword spotting. In Automatic speech and speaker recognition: large margin and kernel methods. New York: Wiley."},{"key":"9217_CR19","volume-title":"Proc. int. conf. acoustics, speech and signal processing","author":"D. Hakkani-Tur","year":"2003","unstructured":"Hakkani-Tur, D., & Riccardi, G. (2003). A general algorithm for word graph matrix decomposition. In Proc. int. conf. acoustics, speech and signal processing, Hong-Kong."},{"key":"9217_CR20","volume-title":"Proc. IEEE workshop on automatic speech recognition and understanding","author":"T. Hazen","year":"2009","unstructured":"Hazen, T., Shen, W., & White, C. (2009). Query-by-example spoken term detection using phonetic posteriorgram templates. In Proc. IEEE workshop on automatic speech recognition and understanding, Merano, Italy."},{"key":"9217_CR21","volume-title":"Proc. int. conf. acoustics, speech and signal processing","author":"M. Huijbregts","year":"2011","unstructured":"Huijbregts, M., McLaren, M., & Leeuwen, D. V. (2011). Unsupervised acoustic sub-word unit detection for query-by-example spoken term detection. In Proc. int. conf. acoustics, speech and signal processing, Prague."},{"key":"9217_CR22","volume-title":"Proc. int. conf. acoustics, speech and signal processing","author":"D. James","year":"1994","unstructured":"James, D., & Young, S. (1994). A fast lattice-based approach to vocabulary independent wordspotting. In Proc. int. conf. acoustics, speech and signal processing, Adelaide, Australia."},{"issue":"8","key":"9217_CR23","doi-asserted-by":"crossref","first-page":"1457","DOI":"10.1109\/TASL.2009.2021307","volume":"17","author":"A. Jansen","year":"2009","unstructured":"Jansen, A., & Niyogi, P. (2009). Point process models for spotting keywords in continuous speech. IEEE Transactions on Audio, Speech, and Language Processing, 17(8), 1457\u20131470.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9217_CR24","volume-title":"Proc. int. conf. speech processing","author":"A. Jansen","year":"2010","unstructured":"Jansen, A., Church, K., & Hermansky, H. (2010). Towards spoken term discovery at scale with zero resources. In Proc. int. conf. speech processing, Chiba, Japan."},{"key":"9217_CR25","volume-title":"Proc. of workshop on non-linear speech processing","author":"J. Keshet","year":"2007","unstructured":"Keshet, J., Grangier, D., & Bengio, S. (2007). Discriminative keyword spotting. In Proc. of workshop on non-linear speech processing, Paris, France."},{"key":"9217_CR26","volume-title":"Proc. int. conf. speech processing","author":"K. Kintzley","year":"2011","unstructured":"Kintzley, K., Jansen, A., & Hermansky, H. (2011). Event selection from phone posteriorgrams using matched filters. In Proc. int. conf. speech processing, Florence, Italy."},{"key":"9217_CR27","unstructured":"Lehtonen, M., Fousek, P., & Hermansky, H. (2005). IDIAP research report: hierarchical approach for spotting keywords."},{"key":"9217_CR28","volume-title":"Proc. ACM special interest group on information retrieval","author":"J. Mamou","year":"2007","unstructured":"Mamou, J., Ramabhadran, B., & Siohan, O. (2007). Vocabulary independent spoken term detection. In Proc. ACM special interest group on information retrieval, New York, USA."},{"issue":"4","key":"9217_CR29","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1006\/csla.2000.0152","volume":"14","author":"L. Mangu","year":"2000","unstructured":"Mangu, L., Brill, E., & Stolcke, A. (2000). Finding consensus in speech recognition: word error minimization and other applications of confusion networks. Computer Speech & Language, 14(4), 373\u2013400.","journal-title":"Computer Speech & Language"},{"issue":"6","key":"9217_CR30","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1109\/TASSP.1980.1163491","volume":"28","author":"C. Meyers","year":"1980","unstructured":"Meyers, C., Rabiner, L., & Rosenberg, A. (1980). Performance tradeoffs in dynamic time warping algorithms for isolated word recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing, 28(6), 623\u2013635.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"9217_CR31","volume-title":"ECAI workshop","author":"M. Mohri","year":"1996","unstructured":"Mohri, M., Pereira, F., Pereira, O., & Reiley, M. (1996). Weighted automata in text and speech processing. In ECAI workshop."},{"issue":"3","key":"9217_CR32","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/S0167-6393(00)00008-X","volume":"32","author":"K. Ng","year":"2000","unstructured":"Ng, K., & Zue, V. (2000). Subwordbased approaches for spoken document retrieval. Speech Communication, 32(3), 157\u2013186.","journal-title":"Speech Communication"},{"key":"9217_CR33","volume-title":"Proc. int. conf. acoustics, speech and signal processing","author":"S. Novotney","year":"2009","unstructured":"Novotney, S., Schwartz, R., & Ma, J. (2009). Unsupervised acoustic and language model training with small amounts of labelled data. In Proc. int. conf. acoustics, speech and signal processing, Taipei, Taiwan."},{"issue":"6","key":"9217_CR34","doi-asserted-by":"crossref","first-page":"1562","DOI":"10.1109\/TASL.2009.2037404","volume":"18","author":"Y. C. Pan","year":"2010","unstructured":"Pan, Y. C., & shan Lee, L. (2010). Performance analysis for lattice-based speech indexing approaches using words and subword units. IEEE Transactions on Audio, Speech, and Language Processing, 18(6), 1562\u20131574.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9217_CR35","volume-title":"Proc. IEEE workshop on automatic speech recognition and understanding","author":"C. Parada","year":"2009","unstructured":"Parada, C., Sethi, A., & Ramabhadran, B. (2009). Query-by-example spoken term detection for oov terms. In Proc. IEEE workshop on automatic speech recognition and understanding, Merano, Italy."},{"issue":"1","key":"9217_CR36","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1109\/TASL.2007.909282","volume":"16","author":"A. S. Park","year":"2008","unstructured":"Park, A. S., & Glass, J. (2008). Unsupervised pattern discovery in speech. IEEE Transactions on Audio, Speech, and Language Processing, 16(1), 186\u2013197.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9217_CR37","volume-title":"Modern methods of speech processing","author":"J. R. Rohlicek","year":"1995","unstructured":"Rohlicek, J. R. (1995). Chapter on word spotting. In Modern methods of speech processing, Norwell: Kluwer Academic."},{"key":"9217_CR38","volume-title":"Automatic speech and speaker recognition: advanced topics","author":"R. C. Rose","year":"1996","unstructured":"Rose, R. C. (1996). Word spotting from continuous speech utterances. In Automatic speech and speaker recognition: advanced topics, Norwell: Kluwer Academic."},{"key":"9217_CR39","volume-title":"Proc. int. conf. acoustics, speech and signal processing","author":"R. C. Rose","year":"1990","unstructured":"Rose, R. C., & Paul, D. B. (1990). A\u00a0hidden Markov model based keyword recognition system. In Proc. int. conf. acoustics, speech and signal processing, Albuquerque, USA."},{"issue":"1","key":"9217_CR40","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/TASSP.1978.1163055","volume":"26","author":"H. Sakoe","year":"1978","unstructured":"Sakoe, H., & Chiba, S. (1978). Dynamic programming algorithm optimization for spoken word recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing, 26(1), 43\u201349.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"9217_CR41","volume-title":"Proc. int. conf. speech and language processing","author":"E. Sandness","year":"2000","unstructured":"Sandness, E., & Hetherington, I. (2000). Keyword-based discriminative training of acoustic models. In Proc. int. conf. speech and language processing, Beijing, China."},{"key":"9217_CR42","volume-title":"HLT-NAACL","author":"M. Saraclar","year":"2004","unstructured":"Saraclar, M., & Sproat, R. W. (2004). Lattice based search for spoken utterance retrieval. In HLT-NAACL, Boston, USA."},{"key":"9217_CR43","volume-title":"Proc. int. conf. speech processing","author":"W. Shen","year":"2009","unstructured":"Shen, W., White, C., & Hazen, T. (2009). A\u00a0comparison of query-by-example methods for spoken term detection. In Proc. int. conf. speech processing, Brighton, UK."},{"key":"9217_CR44","volume-title":"Proc. IEEE workshop on automatic speech recognition and understanding","author":"M. Silaghi","year":"1999","unstructured":"Silaghi, M., & Bourlard, H. (1999). Iterative posterior-based keyword spotting without filler models. In Proc. IEEE workshop on automatic speech recognition and understanding, Colorado, USA."},{"key":"9217_CR45","volume-title":"Proc. int. conf. acoustics, speech and signal processing","author":"R. Sukkar","year":"1996","unstructured":"Sukkar, R., Seltur, A., Rahim, M. G., & Lee, C. H. (1996). Utterance verification of keyword strings using word-based minimum verification error training. In Proc. int. conf. acoustics, speech and signal processing, Atlanta, USA."},{"key":"9217_CR46","volume-title":"Eurospeech","author":"I. Szoke","year":"2005","unstructured":"Szoke, I., Schwarz, P., Patejka, P., Burget, L., Karafiat, M., Fapso, M., & Cernocky, J. (2005). Comparison of keyword spotting approaches for informal continuous speech. In Eurospeech, Lisbon, Portugal."},{"key":"9217_CR47","volume-title":"Spoken language technology workshop","author":"I. Szoke","year":"2008","unstructured":"Szoke, I., Burget, L., Cernocky, J., & Fapso, M. (2008). Sub-word modeling of out-of-vocabulary words in spoken term detection. In Spoken language technology workshop, Goa, India."},{"key":"9217_CR48","volume-title":"ACM workshop on searching spontaneous conversational speech","author":"J. Tejedor","year":"2010","unstructured":"Tejedor, J., Szoke, I., & Fapso, M. (2010). Novel methods for query selection and combination in query-by-example spoken term detection. In ACM workshop on searching spontaneous conversational speech, Firenze, Italy."},{"key":"9217_CR49","volume-title":"Proc. int. conf. acoustics, speech and signal processing","author":"K. Thambiratnam","year":"2005","unstructured":"Thambiratnam, K., & Sridharan, S. (2005). Dynamic match phone-lattice searches for very fast and accurate unrestricted vocabulary keyword spotting. In Proc. int. conf. acoustics, speech and signal processing, Philadelphia, USA."},{"key":"9217_CR50","volume-title":"Proc. int. conf. speech processing","author":"D. Vergyri","year":"2007","unstructured":"Vergyri, D., Shafran, I., Stocke, A., Gadde, R., Akbacak, M., Roark, B., & Wang, W. (2007). The sri\/ogi 2006 spoken term detection system. In Proc. int. conf. speech processing, Antwerp, Belgium."},{"key":"9217_CR51","volume-title":"Int. conf. speech database and assessments","author":"H. Wang","year":"2011","unstructured":"Wang, H., Lee, T., & Leung, C. (2011). Unsupervised spoken term detection with acoustic segment model. In Int. conf. speech database and assessments, China."},{"key":"9217_CR52","volume-title":"Proc. int. conf. acoustics, speech and signal processing","author":"M. Weintraub","year":"1997","unstructured":"Weintraub, M., Beaufays, F., Rivlin, Z., Konig, Y., & Stolcke, A. (1997). Neuralnetwork based measures of confidence for word recognition. In Proc. int. conf. acoustics, speech and signal processing, Munich, Germany."},{"issue":"4","key":"9217_CR53","doi-asserted-by":"crossref","first-page":"35.1","DOI":"10.1145\/1880022.1880029","volume":"13","author":"C. Wright","year":"2010","unstructured":"Wright, C., Ballar, L., Coull, S., Monrose, F., & Masson, G. (2010). Uncovering spoken phrases in encrypted voice over IP conversations. ACM Transactions on Information and System Security, 13(4), 35.1\u201335.30.","journal-title":"ACM Transactions on Information and System Security"},{"key":"9217_CR54","volume-title":"Proc. IEEE workshop on automatic speech recognition and understanding","author":"Y. Zhang","year":"2009","unstructured":"Zhang, Y., & Glass, J. (2009). Unsupervised spoken keyword spotting via segmental dtw on Gaussian posteriorgrams. In Proc. IEEE workshop on automatic speech recognition and understanding, Merano, Italy."},{"key":"9217_CR55","volume-title":"Proc. int. conf. acoustics, speech and signal processing","author":"Y. Zhang","year":"2011","unstructured":"Zhang, Y., & Glass, J. (2011). An inner-product lower-bound estimate for dynamic time warping. In Proc. int. conf. acoustics, speech and signal processing, Prague."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-013-9217-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-013-9217-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-013-9217-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,31]],"date-time":"2019-05-31T00:02:46Z","timestamp":1559260966000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-013-9217-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,12,14]]},"references-count":55,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2014,6]]}},"alternative-id":["9217"],"URL":"https:\/\/doi.org\/10.1007\/s10772-013-9217-1","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,12,14]]}}}