{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T22:40:07Z","timestamp":1746398407856,"version":"3.40.4"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319116792"},{"type":"electronic","value":"9783319116808"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-11680-8_5","type":"book-chapter","created":{"date-parts":[[2014,9,29]],"date-time":"2014-09-29T17:25:41Z","timestamp":1412011541000},"page":"49-60","source":"Crossref","is-referenced-by-count":1,"title":["Improving Acoustic Model for Vietnamese Large Vocabulary Continuous Speech Recognition System Using Deep Bottleneck Features"],"prefix":"10.1007","author":[{"given":"Quoc Bao","family":"Nguyen","sequence":"first","affiliation":[]},{"given":"Tat Thang","family":"Vu","sequence":"additional","affiliation":[]},{"given":"Chi Mai","family":"Luong","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Vu, T.T., Nguyen, D.T., Luong, M.C., Hosom, J.-P.: Vietnamese large vocabulary continuous speech recognition. In: INTERSPEECH (2005)","DOI":"10.21437\/Interspeech.2005-550"},{"key":"5_CR2","unstructured":"Quang, N.H., Nocera, P., Castelli, E., Van Loan, T.: A novel approach in continuous speech recognition for vietnamese. In: SLTU (2008)"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Vu, N.T., Schultz, T.: Vietnamese large vocabulary continuous speech recognition. In: Proc. Automatic Speech Recognition and Understanding (ASRU), Merano, Italy. IEEE (December 2009)","DOI":"10.1109\/ASRU.2009.5373424"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Rabiner, L.R.: A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE, 257\u2013286 (1989)","DOI":"10.1109\/5.18626"},{"key":"5_CR5","volume-title":"Connectionist Speech Recognition: A Hybrid Approach","author":"H.A. Bourlard","year":"1993","unstructured":"Bourlard, H.A., Morgan, N.: Connectionist Speech Recognition: A Hybrid Approach. Kluwer Academic Publishers, Norwell (1993)"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Hermansky, H., Ellis, D.P.W., Sharma, S.: Tandem connectionist feature extraction for conventional hmm systems. In: Proc. ICASSP, pp. 1635\u20131638 (2000)","DOI":"10.1109\/ICASSP.2000.862024"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Grezl, F., Karafiat, M., Kontair, S., Cernocky, J.: Probabilistic and bottle-neck features for lvcsr of meetings. In: 2007 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. V\u2013757\u2013IV\u2013760. IEEE (2007)","DOI":"10.1109\/ICASSP.2007.367023"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Seide, F., Li, G., Yu, D.: Conversational speech transcription using context-dependent deep neural networks. In: Proc. Interspeech 2011, pp. 437\u2013440 (2011)","DOI":"10.21437\/Interspeech.2011-169"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Hinton, G.E., Osindero, S., Teh, Y.-W.: A fast learning algorithm for deep belief nets\u00a018, 1527\u20131554 (2006)","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"5_CR10","first-page":"625","volume":"11","author":"D. Erhan","year":"2010","unstructured":"Erhan, D., Bengio, Y., Courville, A., Manzagol, P.-A., Vincent, P., Bengio, S.: Why does unsupervised pre-training help deep learning? J. Mach. Learn. Res.\u00a011, 625\u2013660 (2010)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Gehring, J., Miao, Y., Metze, F., Waibel, A.: Extracting deep bottleneck features using stacked auto-encoders. In: ICASSP 2013, Vancouver, CA, pp. 3377\u20133381 (2013)","DOI":"10.1109\/ICASSP.2013.6638284"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Metze, F., Sheikh, Z.A.W., Waibel, A., Gehring, J., Kilgour, K., Nguyen, Q.B., Nguyen, V.H.: Models of tone for tonal and non-tonal languages. In: ASRU, pp. 261\u2013266. IEEE (2013)","DOI":"10.1109\/ASRU.2013.6707740"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Ghahremani, P., BabaAli, B., Povey, D., Riedhammer, K., Trmal, J., Khudanpur, S.: A pitch extraction algorithm tuned for automatic speech recognition. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE Signal Processing Society (to appear, May 2014)","DOI":"10.1109\/ICASSP.2014.6854049"},{"key":"5_CR14","unstructured":"Talkin, D.: A robust algorithm for pitch tracking (RAPT). In: Klein, W.B., Palival, K.K. (eds.) Speech Coding and Synthesis. Elsevier (1995)"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Plante, F., Meyer, G.F., Ainsworth, W.A.: A pitch extraction reference database. In: EUROSPEECH. ISCA (1995)","DOI":"10.21437\/Eurospeech.1995-191"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Yu, D., Seltzer, M.L.: Improved bottleneck features using pretrained deep neural networks. In: INTERSPEECH, pp. 237\u2013240 (2011)","DOI":"10.21437\/Interspeech.2011-91"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"T\u00fcske, Z., Schl\u00fcter, R., Ney, H.: Deep hierarchical bottleneck mrasta features for IVCSR. In: ICASSP, pp. 6970\u20136974 (2013)","DOI":"10.1109\/ICASSP.2013.6639013"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Sainath, T.N., Kingsbury, B., Ramabhadran, B.: Auto-encoder bottleneck features using deep belief networks. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4153\u20134156 (2012)","DOI":"10.1109\/ICASSP.2012.6288833"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.-A.: Extracting and composing robust features with denoising autoencoders. In: ICML 2008, pp. 1096\u20131103 (2008)","DOI":"10.1145\/1390156.1390294"},{"key":"5_CR20","unstructured":"Glorot, X., Bordes, A., Bengio, Y.: Domain adaptation for large-scale sentiment classification: A deep learning approach. In: Proceedings of the 28th International Conference on Machine Learning (ICML 2011), pp. 513\u2013520 (2011)"},{"key":"5_CR21","unstructured":"Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motlicek, P., Qian, Y., Schwarz, P., Silovsky, J., Stemmer, G., Vesely, K.: The kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding. IEEE Signal Processing Society, IEEE Catalog No.: CFP11SRW-USB (December 2011)"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Rath, S.P., Povey, D., Vesely, K., Cernocky, J.: Improved feature processing for deep neural networks. In: INTERSPEECH, pp. 109\u2013113. ISCA (2013)","DOI":"10.21437\/Interspeech.2013-48"},{"key":"5_CR23","unstructured":"Nguyen, V.H., Luong, C.M., Vu, T.T.: Applying bottle neck feature for vietnamese speech recognition, pp. 379\u2013388 (2013)"},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Nguyen, Q.B., Gehring, J., Kilgour, K.: A\u00a0Waibel, \u201cOptimizing deep bottleneck feature extraction.\u201d in. In: 2013 IEEE RIVF International Conference on Computing and Communication Technologies, Research, Innovation, and Vision for the Future (RIVF), pp. 152\u2013156 (November 2013)","DOI":"10.1109\/RIVF.2013.6719885"}],"container-title":["Advances in Intelligent Systems and Computing","Knowledge and Systems Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-11680-8_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T22:15:41Z","timestamp":1746396941000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-11680-8_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319116792","9783319116808"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-11680-8_5","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2015]]}}}