{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T03:32:34Z","timestamp":1775878354629,"version":"3.50.1"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2017,10,14]],"date-time":"2017-10-14T00:00:00Z","timestamp":1507939200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1007\/s10772-017-9466-5","type":"journal-article","created":{"date-parts":[[2017,10,14]],"date-time":"2017-10-14T02:32:30Z","timestamp":1507948350000},"page":"1005-1016","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Dravidian language classification from speech signal using spectral and prosodic features"],"prefix":"10.1007","volume":"20","author":[{"given":"Shashidhar G.","family":"Koolagudi","sequence":"first","affiliation":[]},{"given":"Akash","family":"Bharadwaj","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6146-5272","authenticated-orcid":false,"given":"Y. V.","family":"Srinivasa Murthy","sequence":"additional","affiliation":[]},{"given":"Nishaanth","family":"Reddy","sequence":"additional","affiliation":[]},{"given":"Priya","family":"Rao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,10,14]]},"reference":[{"key":"9466_CR1","doi-asserted-by":"crossref","unstructured":"Allen, F., Ambikairajah, E., & Epps, J. (2005). Language identification using warping and the shifted delta cepstrum. In IEEE 7th workshop on multimedia signal processing, pp. 1\u20134. IEEE.","DOI":"10.1109\/MMSP.2005.248554"},{"issue":"3","key":"9466_CR2","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1109\/TASSP.1976.1162800","volume":"24","author":"B Atal","year":"1946","unstructured":"Atal, B., & Rabiner, L. (1946). pattern recognition approach to voiced-unvoiced-silence classification with applications to speech recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing, 24(3), 201\u2013212.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"9466_CR3","unstructured":"Br\u00fcmmer, N., Cumani, S., Glembek, O., Karafi\u00e1t, M., Mat\u011bjka, P., Pe\u0161\u00e1n, J., Plchot, O., Soufifar, M., Villiers, E. D., & Cernock\u1ef3, J. H. (2012). Description and analysis of the brno276 system for lre2011. In Odyssey 2012-the speaker and language recognition workshop."},{"key":"9466_CR4","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-57016-2","volume-title":"Spectral Analysis and Filter Theory in Applied Geophysics: With 23 Tables","author":"Burkhard Buttkus","year":"2000","unstructured":"Buttkus, B. (2000). Spectral Analysis and Filter Theory in Applied Geophysics: With 23 Tables. Berlin: Springer Science & Business Media."},{"key":"9466_CR5","unstructured":"Chandrasekaran, K. (2012). Indeterminacies in howatch\u2019s st. benet\u2019s trilogy. Language in India, 12(12)."},{"issue":"11","key":"9466_CR6","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1109\/29.46561","volume":"37","author":"DG Childers","year":"1989","unstructured":"Childers, D. G., Hahn, M., & Larar, J. N. (1989). Silent and voiced\/unvoiced\/mixed excitation (four-way) classification of speech. IEEE Transactions on Acoustics, Speech and Signal Processing, 37(11), 1771\u20131774.","journal-title":"IEEE Transactions on Acoustics, Speech and Signal Processing"},{"key":"9466_CR7","unstructured":"Ciresan, D. C., Meier, U., Gambardella, L. M., & Schmidhuber, J. (2010). Deep big simple neural nets excel on handwritten digit recognition []. Retrieved July 03, 2014, from: http:\/\/arxiv.orgpdf\/1003.0358 ."},{"key":"9466_CR8","doi-asserted-by":"crossref","unstructured":"Collobert, R., & Weston, J. (2008). A unified architecture for natural language processing: Deep neural networks with multitask learning. In Proceedings of the 25th international conference on machine learning, pp. 160\u2013167. ACM.","DOI":"10.1145\/1390156.1390177"},{"issue":"4","key":"9466_CR9","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N. Dehak","year":"2011","unstructured":"Dehak, N., Kenny, P. J., Dehak, R., Dumouchel, P., & Ouellet, P. (2011). Front-end factor analysis for speaker verification. IEEE Transactions on Audio, Speech, and Language Processing, 19(4), 788\u2013798.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9466_CR10","doi-asserted-by":"crossref","unstructured":"Dehak, N., Torres-Carrasquillo, P. A., Reynolds, D., & Dehak, R. (2011). Language recognition via i-vectors and dimensionality reduction. In Twelfth annual conference of the international speech communication association.","DOI":"10.21437\/Interspeech.2011-328"},{"issue":"3\u20134","key":"9466_CR11","first-page":"197","volume":"7","author":"L Deng","year":"2014","unstructured":"Deng, L., Dong, Y., et al. (2014). Deep learning: Methods and applications. Foundations and Trends\u00ae. Signal Processing, 7(3\u20134), 197\u2013387.","journal-title":"Signal Processing"},{"key":"9466_CR12","doi-asserted-by":"crossref","unstructured":"Dietterich, T. G. (2000). Ensemble methods in machine learning. In Multiple classifier systems, pp. 1\u201315. Springer.","DOI":"10.1007\/3-540-45014-9_1"},{"key":"9466_CR13","unstructured":"Ellis, D. (2005). Reproducing the feature outputs of common programs using matlab and melfcc."},{"key":"9466_CR14","doi-asserted-by":"crossref","unstructured":"Ganapathy, S., Han, K., Thomas, S., Omar, M., Segbroeck, M. V., & Narayanan, S. S. (2014). Robust language identification using convolutional neural network features. In Fifteenth annual conference of the international speech communication association.","DOI":"10.21437\/Interspeech.2014-419"},{"key":"9466_CR15","unstructured":"Gnana S. K., & Deepa, S. N. (2013). Review on methods to fix number of hidden neurons in neural networks. In Mathematical Problems in Engineering."},{"key":"9466_CR16","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A. R., & Hinton, G. (2013). Speech recognition with deep recurrent neural networks. In IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 6645\u20136649. IEEE.","DOI":"10.1109\/ICASSP.2013.6638947"},{"issue":"6","key":"9466_CR17","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., Deng, L., Dong, Y., Dahl, G. E., Mohamed, A. R., Jaitly, N., et al. (2012). Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine, 29(6), 82\u201397.","journal-title":"IEEE Signal Processing Magazine"},{"key":"9466_CR18","volume-title":"Spoken language processing: A guide to theory, algorithm, and system development","author":"X Huang","year":"2001","unstructured":"Huang, X., Acero, A., Hon, H. W., & Reddy, R. (2001). Spoken language processing: A guide to theory, algorithm, and system development. Upper Saddle River: Prentice Hall PTR."},{"key":"9466_CR19","doi-asserted-by":"crossref","DOI":"10.4324\/9780203945315","volume-title":"The Indo-Aryan Languages","author":"D. Jain","year":"2007","unstructured":"Jain, D., & Cardona, G. (2007). The Indo-Aryan Languages. Abingdon: Routledge."},{"key":"9466_CR20","doi-asserted-by":"crossref","unstructured":"Jiang, B., Song, Y., Wei, S., McLoughlin, I. V., & Dai, L. R. (2014). Task-aware deep bottleneck features for spoken language identification. In Proceedings of the 15th annual conference of the international speech communication association (INTERSPECH), Singapore.","DOI":"10.21437\/Interspeech.2014-604"},{"key":"9466_CR21","doi-asserted-by":"crossref","unstructured":"Kumar, K., Kim, C., & Stern, R. M. (2011). Delta-spectral cepstral coefficients for robust speech recognition. In IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 4784\u20134787. IEEE.","DOI":"10.1109\/ICASSP.2011.5947425"},{"issue":"5","key":"9466_CR22","doi-asserted-by":"crossref","first-page":"1136","DOI":"10.1109\/JPROC.2012.2237151","volume":"101","author":"H Li","year":"2013","unstructured":"Li, H., Ma, B., & Lee, K. A. (2013). Spoken language recognition: From fundamentals to practice. Proceedings of the IEEE, 101(5), 1136\u20131159.","journal-title":"Proceedings of the IEEE"},{"key":"9466_CR23","doi-asserted-by":"crossref","unstructured":"Li, H., & Ma, B. (2005). A phonotactic language model for spoken language identification. In Proceedings of the 43rd annual meeting on association for computational linguistics, pp. 515\u2013522. Association for Computational Linguistics.","DOI":"10.3115\/1219840.1219904"},{"key":"9466_CR24","volume-title":"A matlab software tool for speech analysis","author":"P Loizou","year":"1998","unstructured":"Loizou, P. (1998). A matlab software tool for speech analysis. Dallas: Author."},{"key":"9466_CR25","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.csl.2016.03.001","volume":"40","author":"I Lopez-Moreno","year":"2016","unstructured":"Lopez-Moreno, I., Gonzalez-Dominguez, J., Martinez, D., Plchot, O., Gonzalez-Rodriguez, J., & Moreno, P. J. (2016). On the use of deep feedforward neural networks for automatic language identification. Computer Speech and Language, 40, 46\u201359.","journal-title":"Computer Speech and Language"},{"key":"9466_CR26","doi-asserted-by":"crossref","unstructured":"Lopez-Moreno, I., Gonzalez-Dominguez, J., Plchot, O., Martinez, D., Gonzalez-Rodriguez, J., & Moreno, P. (2014). Automatic language identification using deep neural networks. In IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 5337\u20135341. IEEE.","DOI":"10.1109\/ICASSP.2014.6854622"},{"key":"9466_CR27","doi-asserted-by":"crossref","unstructured":"Mart\u00ednez, D., Burget, L., Ferrer, L., & Scheffer, N. (2012). ivector-based prosodic system for language identification. In IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 4861\u20134864. IEEE.","DOI":"10.1109\/ICASSP.2012.6289008"},{"key":"9466_CR28","doi-asserted-by":"crossref","unstructured":"Matejka, P., Burget, L., Schwarz, P., & Cernocky, J. (2006). Brno university of technology system for nist 2005 language recognition evaluation. In The IEEE Odyssey speaker and language recognition workshop, pp. 1\u20137. IEEE.","DOI":"10.1109\/ODYSSEY.2006.248093"},{"key":"9466_CR29","doi-asserted-by":"crossref","unstructured":"Matejka, P., Schwarz, P., Cernock\u1ef3, J., & Chytil, P. (2005). Phonotactic language identification using high quality phoneme recognition. In Interspeech, pp. 2237\u20132240.","DOI":"10.21437\/Interspeech.2005-708"},{"issue":"1","key":"9466_CR30","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1109\/TASL.2011.2109382","volume":"20","author":"Abdel-rahman Mohamed","year":"2012","unstructured":"Mohamed, A. R., Dahl, G. E., & Hinton, G. (2012). Acoustic modeling using deep belief networks. IEEE Transactions on Audio, Speech, and Language Processing, 20(1), 14\u201322.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9466_CR31","unstructured":"Montavon, G. (2009). Deep learning for spoken language identification. In NIPS workshop on deep learning for speech recognition and related applications."},{"key":"9466_CR32","volume-title":"Biometrics","author":"T Nanavati","year":"2002","unstructured":"Nanavati, T. (2002). Biometrics. New York: Wiley."},{"key":"9466_CR33","doi-asserted-by":"crossref","unstructured":"Ng, R.W., Leung, C.C., Lee, T., Ma, B., & Li, H. (2010). Prosodic attribute model for spoken language identification. In IEEE international conference on acoustics speech and signal processing (ICASSP), pp. 5022\u20135025. IEEE.","DOI":"10.1109\/ICASSP.2010.5495070"},{"key":"9466_CR34","doi-asserted-by":"crossref","unstructured":"Pinto, J., Yegnanarayana, B., Hermansky, H., & Doss, M. M. (2008). Exploiting contextual information for improved phoneme recognition. In IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 4449\u20134452. IEEE.","DOI":"10.1109\/ICASSP.2008.4518643"},{"key":"9466_CR35","doi-asserted-by":"crossref","unstructured":"Prahallad, K., Kumar E. N., Keri V., Rajendran, S., & Black, A. W. (2012). In INTERSPEECH TheIIIT-HIndic speech databases.","DOI":"10.21437\/Interspeech.2012-659"},{"key":"9466_CR36","doi-asserted-by":"crossref","unstructured":"Ranjan, S., Yu, C., Zhang, C., Kelly, F., & Hansen, J. H. (2016). Language recognition using deep neural networks with very limited training data. In IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 5830\u20135834. IEEE.","DOI":"10.1109\/ICASSP.2016.7472795"},{"key":"9466_CR38","volume-title":"Language Identification Using Excitation Source Features","author":"K Sreenivasa Rao","year":"2015","unstructured":"Rao, K. S., & Nandi, D. (2015). Language Identification Using Excitation Source Features. Berlin: Springer."},{"key":"9466_CR37","unstructured":"Singer, E., Torres-Carrasquillo, P., Reynolds, D. A., McCree, A., Richardson, F., Dehak, N., & Sturim, D. (2012). The mitll nist lre 2011 language recognition system. In IEEE international conference on acoustics speech and signal processing (ICASSP), pp. 209\u2013215."},{"key":"9466_CR39","doi-asserted-by":"crossref","unstructured":"Sturim, D., Campbell, W., Dehak, N., Karam, Z., McCree, A., Reynolds, D., Richardson, F., Torres-Carrasquillo, P., & Shum, S. (2011). The mit ll 2010 speaker recognition evaluation system: Scalable language-independent speaker recognition. In IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 5272\u20135275. IEEE.","DOI":"10.1109\/ICASSP.2011.5947547"},{"key":"9466_CR40","doi-asserted-by":"crossref","unstructured":"Torres-Carrasquillo, P. A., Reynolds, D., & Deller, J. R. Jr. (2002). Language identification usingGaussian mixture model tokenization. In IEEE international conference on acoustics, speech, and signal processing (ICASSP) (Vol. 1, pp. I\u2013757). IEEE.","DOI":"10.1109\/ICASSP.2002.1005850"},{"key":"9466_CR41","doi-asserted-by":"crossref","unstructured":"Torres-Carrasquillo, P. A., Singer, E., Kohler, M. A., Greene, R. J., Reynolds, D. A., & Deller\u00a0Jr., J. R. (2002). Approaches to language identification using Gaussian mixture models and shifted delta cepstral features. In Interspeech.","DOI":"10.21437\/ICSLP.2002-74"},{"key":"9466_CR42","doi-asserted-by":"crossref","unstructured":"Torres-Carrasquillo P. A., Singer E., Gleason T., McCree A., Reynolds D. A., Richardson F., & Sturim, D. (2010). The mitll nist lre 2009 language recognition system. In IEEE international conference on acoustics speech and signal processing (ICASSP), pp. 4994\u20134997. IEEE.","DOI":"10.1109\/ICASSP.2010.5495080"},{"key":"9466_CR43","unstructured":"Young, S., Evermann, G., Gales, M., Hain, T., Kershaw, D., Liu, X., Moore, G., Odell, J., Ollason, D., & Povey, D. (1997). In The HTK book (Vol. 2. Entropic Cambridge Research Laboratory Cambridge)."},{"issue":"1","key":"9466_CR44","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1109\/TSA.1996.481450","volume":"4","author":"MA Zissman","year":"1996","unstructured":"Zissman, M. A. (1996). Comparison of four approaches to automatic language identification of telephone speech. IEEE Transactions on Speech and Audio Processing, 4(1), 31.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9466_CR45","doi-asserted-by":"crossref","unstructured":"Zissman, M. A. (1995). Language identification using phoneme recognition and phonotactic language modeling. In International conference on acoustics, speech, and signal processing (ICASSP) (Vol. 5, pp. 3503\u20133506). IEEE.","DOI":"10.1109\/ICASSP.1995.479741"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-017-9466-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-017-9466-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-017-9466-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,4]],"date-time":"2022-08-04T16:26:00Z","timestamp":1659630360000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-017-9466-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10,14]]},"references-count":45,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2017,12]]}},"alternative-id":["9466"],"URL":"https:\/\/doi.org\/10.1007\/s10772-017-9466-5","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,10,14]]}}}