{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T08:45:55Z","timestamp":1648543555527},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2014,2,1]],"date-time":"2014-02-01T00:00:00Z","timestamp":1391212800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1186\/1687-4722-2014-4","type":"journal-article","created":{"date-parts":[[2014,2,1]],"date-time":"2014-02-01T14:01:33Z","timestamp":1391263293000},"source":"Crossref","is-referenced-by-count":2,"title":["Integrated exemplar-based template matching and statistical modeling for continuous speech recognition"],"prefix":"10.1186","volume":"2014","author":[{"given":"Xie","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunxin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,2,1]]},"reference":[{"issue":"5","key":"100_CR1","first-page":"360","volume":"4","author":"M Ostendorf","year":"1996","unstructured":"Ostendorf M, Digalakis V, Kimball OA: From HMMs to segment models: a unified view of stochastic modeling for speech recognition. IEEE Trans on SAP 1996, 4(5):360-378.","journal-title":"IEEE Trans on SAP"},{"issue":"1","key":"100_CR2","first-page":"52","volume":"ASSP-34","author":"S Furui","year":"1986","unstructured":"Furui S: Speaker-independent isolated word recognition using dynamic features of speech spectrum. IEEE Trans SAP 1986, ASSP-34(1):52-59.","journal-title":"IEEE Trans SAP"},{"key":"100_CR3","first-page":"466","volume-title":"Proc of ICSLP1","author":"H Gish","year":"1996","unstructured":"Gish H, Ng K: Parametric trajectory models for speech recognition. Proc of ICSLP1 1996, 466-469."},{"issue":"2\u20133","key":"100_CR4","first-page":"13","volume":"17","author":"J Glass","year":"2003","unstructured":"Glass J: A probabilistic framework for segment-based speech recognition. Computer Speech and Language 2003, 17(2\u20133):13-152.","journal-title":"Computer Speech and Language"},{"key":"100_CR5","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1109\/ASRU.2009.5372916","volume-title":"IEEE Workshop on Automatic Speech Recognition & Understanding","author":"G Zweig","year":"2009","unstructured":"Zweig G, Nguyen P: A segmental CRF approach to large vocabulary continuous speech recognition. In IEEE Workshop on Automatic Speech Recognition & Understanding. Merano; 2009:152-157."},{"key":"100_CR6","first-page":"145","volume-title":"Proceedings of IEEE Workshop on Automatic Speech Recognition and Understanding","author":"L Deng","year":"2005","unstructured":"Deng L, Yu D, Acero A: A long-contextual-span model of resonance dynamics for speech recognition: parameter learning and recognizer evaluation. In Proceedings of IEEE Workshop on Automatic Speech Recognition and Understanding. San Juan; 2005:145-150."},{"key":"100_CR7","first-page":"4692","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"K Demuynck","year":"2011","unstructured":"Demuynck K, Seppi D, van Hamme H, van Compernolle D: Progress in example based automatic speech recognition. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Prague; 2011:4692-4695."},{"key":"100_CR8","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1109\/MSP.2012.2208663","volume":"29","author":"TN Sainath","year":"2012","unstructured":"Sainath TN, Ramabhadran B, Nahamoo D, Kanevsky D, van Compernolle D, Demuynck K, Gemmeke JF, Bellegarda JR, Sundaram S: Exemplar-based processing for speech recognition. IEEE Signal Process. Mag 2012, 29: 98-113.","journal-title":"IEEE Signal Process. Mag"},{"key":"100_CR9","doi-asserted-by":"crossref","first-page":"2254","DOI":"10.21437\/Interspeech.2010-619","volume-title":"Proceedings of INTERSPEECH 2010","author":"TN Sainath","year":"2010","unstructured":"Sainath TN, Ramabhadran B, Nahamoo S, Kanevsky S, Sethy A: Exemplar-based sparse representation features for speech recognition. In Proceedings of INTERSPEECH 2010. Makuhari; 2010:2254-2257."},{"issue":"4","key":"100_CR10","first-page":"1377","volume":"15","author":"M de Wachter","year":"2007","unstructured":"de Wachter M, Matton M, Demuynck K, Wambacq P, Cools R, van Compernolle D: Template-based continuous speech recognition. IEEE Trans ASLP 2007, 15(4):1377-1390.","journal-title":"IEEE Trans ASLP"},{"key":"100_CR11","doi-asserted-by":"crossref","first-page":"74","DOI":"10.21437\/Interspeech.2010-15","volume-title":"Proceedings of INTERSPEECH 2010","author":"X Sun","year":"2010","unstructured":"Sun X, Zhao Y: Integrate template matching and statistical modeling for speech recognition. In Proceedings of INTERSPEECH 2010. Makuhari; 2010:74-77."},{"key":"100_CR12","volume-title":"Fundamentals of Speech Recognition","author":"L Rabiner","year":"1993","unstructured":"Rabiner L, Juang B: Fundamentals of Speech Recognition. Englewood Cliffs: Prentice Hall; 1993."},{"key":"100_CR13","doi-asserted-by":"crossref","first-page":"3067","DOI":"10.21437\/Interspeech.2009-570","volume-title":"Proceedings of INTERSPEECH 2009","author":"S Demange","year":"2009","unstructured":"Demange S, van Compernolle D: HEAR: an hybrid episodic-abstract speech recognizer. In Proceedings of INTERSPEECH 2009. Brighton; 2009:3067-3070."},{"key":"100_CR14","doi-asserted-by":"crossref","first-page":"1954","DOI":"10.21437\/Interspeech.2010-99","volume-title":"Proceedings of INTERSPEECH 2010","author":"L Golipour","year":"2010","unstructured":"Golipour L, O\u2019Shaughnessy D: Phoneme classification and lattice rescoring based on a k-NN approach. In Proceedings of INTERSPEECH 2010. Makuhari; 2010:1954-1957."},{"key":"100_CR15","first-page":"5048","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"K Demuynck","year":"2011","unstructured":"Demuynck K, Demuynck K, Seppi D, van Compernolle D, Nguyen P, Zweig G: Integrating meta-information into exemplar-based speech recognition with segmental conditional random fields. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Prague; 2011:5048-5051."},{"key":"100_CR16","doi-asserted-by":"crossref","first-page":"881","DOI":"10.21437\/Interspeech.2010-296","volume-title":"Proceedings of INTERSPEECH 2010","author":"S Sundaram","year":"2010","unstructured":"Sundaram S, Bellegarda JR: Latent perceptual mapping: a new acoustic modeling framework for speech recognition. In Proceedings of INTERSPEECH 2010. Makuhari; 2010:881-884."},{"key":"100_CR17","doi-asserted-by":"crossref","first-page":"985","DOI":"10.21437\/Interspeech.2011-405","volume-title":"Proceedings of INTERSPEECH 2011","author":"X Sun","year":"2011","unstructured":"Sun X, Zhao Y: New methods for template selection and compression in continuous speech recognition. In Proceedings of INTERSPEECH 2011. Florence; 2011:985-988."},{"key":"100_CR18","doi-asserted-by":"crossref","first-page":"545","DOI":"10.21437\/Interspeech.2011-227","volume-title":"Proceedings of INTERSPEECH 2011","author":"D Seppi","year":"2011","unstructured":"Seppi D, Demuynck K, van Compernolle D: Template-based automatic speech recognition meets prosody. In Proceedings of INTERSPEECH 2011. Florence; 2011:545-548."},{"key":"100_CR19","doi-asserted-by":"crossref","first-page":"901","DOI":"10.21437\/Interspeech.2010-301","volume-title":"Proceedings of INTERSPEECH 2010","author":"D Seppi","year":"2010","unstructured":"Seppi D, Van Compernolle D: Data pruning for template-based automatic speech recognition. In Proceedings of INTERSPEECH 2010. Makuhari; 2010:901-904."},{"key":"100_CR20","first-page":"4125","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"S Sundaram","year":"2012","unstructured":"Sundaram S, Bellegarda J: Latent perceptual mapping with data driven variable-length acoustic units for template-based speech recognition. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Kyoto; 2012:4125-4128."},{"key":"100_CR21","first-page":"4437","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"G Heigold","year":"2012","unstructured":"Heigold G, Nguyen P, Weintraub M, Vanhoucke V: Investigations on exemplar-based features for speech recognition towards thousands of hours of unsupervised, noisy data. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Kyoto; 2012:4437-4440."},{"key":"100_CR22","first-page":"3849","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"J Ming","year":"2009","unstructured":"Ming J: Maximizing the continuity in segmentation- a new approach to model, segment and recognize speech. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Taiwan; 2009:3849-3852."},{"issue":"7","key":"100_CR23","first-page":"1355","volume":"21","author":"J Ming","year":"2013","unstructured":"Ming J, Srinivasan R, Crookes D, Jafari A: CLOSE\u2014a data-driven approach to speech separation. IEEE Trans ASLP 2013, 21(7):1355-1368.","journal-title":"IEEE Trans ASLP"},{"key":"100_CR24","first-page":"123","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, (ICASSP), vol. 1","author":"A Garcia","year":"2006","unstructured":"Garcia A, Gish H: Keyword spotting of arbitrary words using minimal speech resources. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, (ICASSP), vol. 1. Atlanta; 2006:123-127."},{"key":"100_CR25","volume-title":"IEEE Workshop on Automatic Speech Recognition & Understanding","author":"T Hazen","year":"2009","unstructured":"Hazen T, Shen W, White C: Query-by-example spoken term detection using phonetic posteriorgram templates. In IEEE Workshop on Automatic Speech Recognition & Understanding. Merano; 2009."},{"key":"100_CR26","volume-title":"IEEE Workshop on Automatic Speech Recognition & Understanding","author":"Y Zhang","year":"2009","unstructured":"Zhang Y, Glass J: Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams. In IEEE Workshop on Automatic Speech Recognition & Understanding. Merano; 2009."},{"key":"100_CR27","volume-title":"Proceedings of the DARPA Speech Recognition Workshop","author":"L Lamel","year":"1989","unstructured":"Lamel L, Kassel R, Seneff S: Speech database development: design and analysis of the acoustic-phonetic corpus. Proceedings of the DARPA Speech Recognition Workshop 1989."},{"key":"100_CR28","first-page":"957","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Y Zhao","year":"2006","unstructured":"Zhao Y, Zhang X, Hu R, Xue J, Li X, Che L, Hu R, Schopp L: An automatic captioning system for telemedicine. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Toulouse; 2006:957-960."},{"issue":"4","key":"100_CR29","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1080\/00031305.1987.10475510","volume":"41","author":"S Kullback","year":"1987","unstructured":"Kullback S: Letter to the editor: the Kullback\u2013Leibler distance. Am. Stat 1987, 41(4):338-341.","journal-title":"Am. Stat"},{"key":"100_CR30","first-page":"317","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol 4","author":"JR Hershey","year":"2007","unstructured":"Hershey JR, Olsen PA: Approximating the Kullback\u2013Leibler divergence between Gaussian mixture models. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol 4. Hawaii; 2007:317-320."},{"key":"100_CR31","volume-title":"The HTK Book","author":"S Young","year":"2009","unstructured":"Young S, Evermann G, Gales M, Hain T, Kershaw D, Liu X, Moore G, Odell J, Ollason D, Valtchev V, Woodland P: The HTK Book. Cambridge: Cambridge University Engineering Department; 2009."},{"key":"100_CR32","volume-title":"Pattern Classification","author":"R Duda","year":"2009","unstructured":"Duda R, Hart P, Stork D: Pattern Classification. 2nd edition. New York: Wiley; 2009.","edition":"2"},{"key":"100_CR33","volume-title":"Pattern Recognition","author":"S Theodoridis","year":"2006","unstructured":"Theodoridis S, Koutroumbas K: Pattern Recognition. 3rd edition. San Diego: Academic Press; 2006.","edition":"3"},{"key":"100_CR34","volume-title":"Proceedings of EUROSPEECH","author":"A Sankar","year":"1995","unstructured":"Sankar A, Beaufays F, Digalakis V: Training data clustering for improved speech recognition. In Proceedings of EUROSPEECH. Madrid; 1995."},{"key":"100_CR35","first-page":"506","volume-title":"Third International Symposium on IITA","author":"Y Li","year":"2009","unstructured":"Li Y, Li L: A greedy merge learning algorithm for Gaussian Mixture Model. Third International Symposium on IITA 2009, 506-509. vol. 2, Nanchang, 21\u201322 November 2009"},{"issue":"11","key":"100_CR36","doi-asserted-by":"publisher","first-page":"1641","DOI":"10.1109\/29.46546","volume":"37","author":"KF Lee","year":"1989","unstructured":"Lee KF, Hon HW: Speaker-independent phone recognition using hidden Markov models. IEEE Trans ASSP 1989, 37(11):1641-1648. 10.1109\/29.46546","journal-title":"IEEE Trans ASSP"},{"issue":"3","key":"100_CR37","first-page":"332","volume":"11","author":"X Zhang","year":"2007","unstructured":"Zhang X, Zhao Y, Schopp L: A novel method of language modeling for automatic captioning in telemedicine. IEEE Trans ITB 2007, 11(3):332-337.","journal-title":"IEEE Trans ITB"},{"issue":"1","key":"100_CR38","first-page":"14","volume":"20","author":"A Mohamed","year":"2012","unstructured":"Mohamed A, Dahl G, Hinton G: Acoustic modeling using deep belief networks. IEEE Trans ASLP 2012, 20(1):14-22.","journal-title":"IEEE Trans ASLP"},{"key":"100_CR39","first-page":"24","volume-title":"Proceedings of IEEE Workshop on Automatic Speech Recognition & Understanding","author":"F Seide","year":"2011","unstructured":"Seide F, Li G, Chen X, Yu D: Feature engineering in context-dependent deep neural networks for conversational speech transcription. In Proceedings of IEEE Workshop on Automatic Speech Recognition & Understanding. Hawaii; 2011:24-29."},{"key":"100_CR40","first-page":"8614","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"TN Sainath","year":"2013","unstructured":"Sainath TN, Mohamed A, Kingsbury B, Ramabhadran B: Deep convolutional neural networks for LVCSR. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Vancouver; 2013:8614-8618."},{"key":"100_CR41","first-page":"2163","volume-title":"Proceedings of INTERSPEECH","author":"X Sun","year":"2011","unstructured":"Sun X, Chen X, Zhao Y: On the effectiveness of statistical modeling based template matching approach for continuous speech recognition. In Proceedings of INTERSPEECH. Florence; 2011:2163-2166."}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1687-4722-2014-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-4722-2014-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-4722-2014-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,25]],"date-time":"2022-03-25T01:40:55Z","timestamp":1648172455000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/1687-4722-2014-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,2,1]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,12]]}},"alternative-id":["100"],"URL":"https:\/\/doi.org\/10.1186\/1687-4722-2014-4","relation":{},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,2,1]]},"article-number":"4"}}