{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T11:48:23Z","timestamp":1751456903717},"reference-count":16,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2016,5,5]],"date-time":"2016-05-05T00:00:00Z","timestamp":1462406400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst"],"published-print":{"date-parts":[[2017,7]]},"DOI":"10.1007\/s11265-016-1133-6","type":"journal-article","created":{"date-parts":[[2016,5,5]],"date-time":"2016-05-05T06:21:55Z","timestamp":1462429315000},"page":"91-102","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Improvements in IITG Assamese Spoken Query System: Background Noise Suppression and Alternate Acoustic Modeling"],"prefix":"10.1007","volume":"88","author":[{"given":"S.","family":"Shahnawazuddin","sequence":"first","affiliation":[]},{"given":"Deepak","family":"Thotappa","sequence":"additional","affiliation":[]},{"given":"Abhishek","family":"Dey","sequence":"additional","affiliation":[]},{"given":"Siddika","family":"Imani","sequence":"additional","affiliation":[]},{"given":"S. R.","family":"M. Prasanna","sequence":"additional","affiliation":[]},{"given":"Rohit","family":"Sinha","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,5,5]]},"reference":[{"key":"1133_CR1","unstructured":"Kaldi Toolkit: http:\/\/kaldi.sourceforge.net ."},{"issue":"1","key":"1133_CR2","first-page":"30","volume":"20","author":"G Dahl","year":"2012","unstructured":"Dahl, G., Yu, D., Deng, L., & Acero, A. (2012). Context-dependent pre-trained deep neural networks for large vocabulary speech recognition. IEEE Transactions on Audio Speech, and Language Processing (receiving 2013 IEEE SPS Best Paper Award), 20(1), 30\u201342.","journal-title":"IEEE Transactions on Audio Speech, and Language Processing (receiving 2013 IEEE SPS Best Paper Award)"},{"key":"1133_CR3","doi-asserted-by":"crossref","unstructured":"Deepak, K.T., Sarma, B.D., & Prasanna, S.R.M. (2012). Foreground speech segmentation using zero frequency filtered signal. In Proc. Interspeech.","DOI":"10.21437\/Interspeech.2012-427"},{"key":"1133_CR4","unstructured":"Glass, J.R. (1999). Challanges for spoken dialogue systems. In Proc. IEEE ASRU workshop."},{"key":"1133_CR5","doi-asserted-by":"crossref","unstructured":"Hinton, G.E., Deng, L., Yu, D., Dahl, G., Mohamed, A.R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., & Kingsbury, B. (2012). Deep neural networks for acoustic modeling in speech recognition. Signal Processing Magazine.","DOI":"10.1109\/MSP.2012.2205597"},{"issue":"7","key":"1133_CR6","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"GE Hinton","year":"2006","unstructured":"Hinton, G.E., Osindero, S., & Teh, Y.W. (2006). A fast learning algorithm for deep belief nets. Neural Computer, 18(7), 1527\u20131554.","journal-title":"Neural Computer"},{"key":"1133_CR7","doi-asserted-by":"crossref","first-page":"1602","DOI":"10.1109\/TASL.2008.2004526","volume":"16","author":"KSR Murthy","year":"2008","unstructured":"Murthy, K.S.R., & Yegnanarayana, B. (2008). Epoch extraction from speech signals. IEEE Transaction Audio, Speech and Language Processing, 16, 1602\u20131613.","journal-title":"IEEE Transaction Audio, Speech and Language Processing"},{"key":"1133_CR8","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1109\/LSP.2009.2016829","volume":"16","author":"KSR Murthy","year":"2009","unstructured":"Murthy, K.S.R., & Yegnanarayana, B. (2009). Characterization of glottal activity from speech signals. IEEE Signal Processing Letters, 16, 469\u2013472 .","journal-title":"IEEE Signal Processing Letters"},{"issue":"2","key":"1133_CR9","doi-asserted-by":"crossref","first-page":"404","DOI":"10.1016\/j.csl.2010.06.003","volume":"25","author":"D Povey","year":"2011","unstructured":"Povey, D., Burget, L., Agarwal, M., Akyazi, P., Kai, F., Ghoshal, A., Glembek, O., Goel, N., Karafi\u00e1t, M., Rastrow, A., Rose, R.C., Schwarz, P., & Thomas, S. (2011). The subspace gaussian mixture model-a structured model for speech recognition. Computer Speech and Language, 25(2), 404\u2013439.","journal-title":"Computer Speech and Language"},{"key":"1133_CR10","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. (2011). The kaldi speech recognition toolkit. In Proc. ASRU."},{"key":"1133_CR11","doi-asserted-by":"crossref","unstructured":"Rabiner, L.R. (1994). Applications of voice processing to telecommunications. In Proc. IEEE (Vol. 82, pp. 199\u2013228).","DOI":"10.1109\/5.265347"},{"key":"1133_CR12","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1002\/j.1538-7305.1975.tb02840.x","volume":"54","author":"LR Rabiner","year":"1975","unstructured":"Rabiner, L.R., & Sambur, M.R. (1975). An algorithm for determining the endpoints of isolated utterances. Bell System Technical Journal, 54, 297\u2013315.","journal-title":"Bell System Technical Journal"},{"key":"1133_CR13","doi-asserted-by":"crossref","unstructured":"Rose, R.C., Yin, S.C., & Tang, Y. (2011). An investigation of subspace modeling for phonetic and speaker variability in automatic speech recognition. In Proc. ICASSP (pp. 4508\u20134511).","DOI":"10.1109\/ICASSP.2011.5947356"},{"key":"1133_CR14","unstructured":"Shahnawazuddin, S., Deepak, K.T., Sarma, B.D., Deka, A., Prasanna, S.R.M., & Sinha, R. (2014). Low complexity on-line adaptation techniques in context of assamese spoken query system. Journal of Signal Processing Systems, 1\u201315."},{"key":"1133_CR15","doi-asserted-by":"crossref","unstructured":"Trihandoyo, A., Belloum, A., & Hou, K.M. (1995). A real-time speech recognition architecture for a multi-channel interactive voice response system. In Proc. ICASSP (Vol. 4, pp. 2687\u20132690).","DOI":"10.1109\/ICASSP.1995.480115"},{"issue":"4","key":"1133_CR16","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1016\/j.csl.2011.03.001","volume":"25","author":"H Xu","year":"2011","unstructured":"Xu, H., Povey, D., Mangu, L., & Zhu, J. (2011). Minimum bayes risk decoding and system combination based on a recursion for edit distance. Computer Speech and Language, 25(4), 802\u2013828.","journal-title":"Computer Speech and Language"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-016-1133-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-016-1133-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-016-1133-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-016-1133-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,19]],"date-time":"2022-06-19T23:56:32Z","timestamp":1655682992000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-016-1133-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,5,5]]},"references-count":16,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,7]]}},"alternative-id":["1133"],"URL":"https:\/\/doi.org\/10.1007\/s11265-016-1133-6","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"value":"1939-8018","type":"print"},{"value":"1939-8115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,5,5]]}}}