{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T20:18:56Z","timestamp":1775247536765,"version":"3.50.1"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2018,10,12]],"date-time":"2018-10-12T00:00:00Z","timestamp":1539302400000},"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":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1007\/s00034-018-0962-x","type":"journal-article","created":{"date-parts":[[2018,10,12]],"date-time":"2018-10-12T01:13:56Z","timestamp":1539306836000},"page":"2266-2296","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["A Pre-classification-Based Language Identification for Northeast Indian Languages Using Prosody and Spectral Features"],"prefix":"10.1007","volume":"38","author":[{"given":"Chuya","family":"China Bhanja","sequence":"first","affiliation":[]},{"given":"Mohammad Azharuddin","family":"Laskar","sequence":"additional","affiliation":[]},{"given":"Rabul Hussain","family":"Laskar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,12]]},"reference":[{"key":"962_CR1","doi-asserted-by":"crossref","unstructured":"A.G. Adami, R. Mihaescu, D.A. Reynolds, J.J. Godfrey, Modeling prosodic dynamics for speaker recognition, in Proceedings, IEEE International Conference on Acoustic, Speech Signal Process, vol. 4 (Hong Kong, 2003), pp. 788\u2013791","DOI":"10.1109\/ICASSP.2003.1202761"},{"key":"962_CR2","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-017-0724-1","author":"F Adeeba","year":"2017","unstructured":"F. Adeeba, S. Hussain, Acoustic feature analysis and discriminative modeling for language identification of closely related South-Asian languages. Circuits System Signal Process. (2017). https:\/\/doi.org\/10.1007\/s00034-017-0724-1","journal-title":"Circuits System Signal Process."},{"issue":"4","key":"962_CR3","first-page":"151","volume":"10","author":"CL Alan","year":"2010","unstructured":"C.L. Alan, Tonal effects on perceived vowel duration. Lab. Phonol. 10(4), 151\u2013168 (2010)","journal-title":"Lab. Phonol."},{"issue":"2","key":"962_CR4","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MCAS.2011.941081","volume":"11","author":"E Ambikairajah","year":"2011","unstructured":"E. Ambikairajah, H. Li, L. Wang, B. Yin, V. Sethu, Language identification: a tutorial. IEEE Circuits Syst. Mag. 11(2), 82\u2013108 (2011)","journal-title":"IEEE Circuits Syst. Mag."},{"key":"962_CR5","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/S0095-4470(03)00039-1","volume":"32","author":"M Atterer","year":"2004","unstructured":"M. Atterer, D.R. Ladd, On the phonetics and phonology of \u201csegmental anchoring\u201d of F 0. J. Phonetics 32, 177\u2013197 (2004)","journal-title":"J. Phonetics"},{"key":"962_CR6","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0610848104","author":"D Dan","year":"2007","unstructured":"D. Dan, D. Robert Ladd, Linguistic tone is related to the population frequency of the adaptive haplogroups of two brain size genes, ASPM and microcephalin. PANS (2007). https:\/\/doi.org\/10.1073\/pnas.0610848104","journal-title":"PANS"},{"issue":"4","key":"962_CR7","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"99","author":"N Dehak","year":"2010","unstructured":"N. Dehak, P. Kenny, R. Dehak, P. Dumouchel, P. Ouellet, Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 99(4), 788\u2013798 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"962_CR8","doi-asserted-by":"crossref","unstructured":"N. Dehak, P. Torres-Carrasquillo, D. Reynolds, R. Dehak, Language recognition via i-vectors and dimensionality reduction, in Interspeech Conference (Florence, 2011), pp. 857\u2013860","DOI":"10.21437\/Interspeech.2011-328"},{"key":"962_CR9","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.specom.2017.01.009","volume":"88","author":"S Dey","year":"2017","unstructured":"S. Dey, P. Motlicek, S. Madikeri, M. Ferras, Template-matching for text-dependent speaker verification. Speech Commun. 88, 96\u2013105 (2017)","journal-title":"Speech Commun."},{"key":"962_CR10","unstructured":"M. Dorofki, A.H. Elshafie, O. Gaafar, O.A. Karim, S. Mastura, Comparison of artificial neural network transfer functions abilities to simulate extreme runoff data, in International Conference on Environment, Energy and Biotechnology (Singapore, 2012)"},{"issue":"4","key":"962_CR11","first-page":"891","volume":"5","author":"S Duanmu","year":"2004","unstructured":"S. Duanmu, Tone and non-tone languages: an alternative to language typology and parameters. Lang. Linguist. 5(4), 891\u2013923 (2004)","journal-title":"Lang. Linguist."},{"key":"962_CR12","doi-asserted-by":"crossref","unstructured":"S. Dusan, L. Deng, Recovering vocal tract shapes from MFCC parameters, in 5th International Conference on Spoken Language Processing (1998)","DOI":"10.21437\/ICSLP.1998-795"},{"issue":"5","key":"962_CR13","doi-asserted-by":"publisher","first-page":"1322","DOI":"10.1073\/pnas.1417413112","volume":"112","author":"C Everett","year":"2016","unstructured":"C. Everett, D. Bas\u00ec, S.G. Roberts, Climate, vocal folds, and tonal languages: connecting the physiological and geographical dots. PNAS 112(5), 1322\u20131327 (2016)","journal-title":"PNAS"},{"issue":"2","key":"962_CR14","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/0024-3841(77)90054-7","volume":"41","author":"J Gandour","year":"1977","unstructured":"J. Gandour, Counterfeit tones in the speech of Southern Thai bidialectals. Lingua 41(2), 125\u2013143 (1977)","journal-title":"Lingua"},{"key":"962_CR15","volume-title":"Computational Linguistics and Intelligent Text Processing, Part-1","author":"A Gelbukh","year":"2011","unstructured":"A. Gelbukh, Computational Linguistics and Intelligent Text Processing, Part-1 (Springer, Berlin, 2011)"},{"key":"962_CR16","unstructured":"A.O. Hatch, S. Kajarekar, A. Stolcke, Within-class covariance normalization for SVM-based speaker recognition, in Proceeding of the ICSLP (2006), pp. 1471\u20131474"},{"issue":"3","key":"962_CR17","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1016\/j.dsp.2011.11.008","volume":"22","author":"S Jothilakshmi","year":"2012","unstructured":"S. Jothilakshmi, V. Ramalingam, S. Palanivel, A hierarchical language identification system for Indian languages. Digit. Signal Proc. 22(3), 544\u2013553 (2012)","journal-title":"Digit. Signal Proc."},{"key":"962_CR18","unstructured":"A.N. Khan, S.V. Gangashetty, B. Yegnanarayana, Syllabic properties of three Indian languages: implications for speech recognition and language identification, in International Conference on Natural Language Processing (Mysore, 2003), pp. 125\u2013134"},{"key":"962_CR19","unstructured":"E. Kidder, Tone, intonation, stress and duration in Navajo. in En Linguistic Theory at the University of Arizona, eds. by Mans Hulden y Shannon T. Bischoff (Arizona: University of Arizona Linguistics Circle, 2008), Vol. 16, pp 55\u201366"},{"key":"962_CR20","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1006\/jpho.1999.0089","volume":"27","author":"RA Krakow","year":"1999","unstructured":"R.A. Krakow, Physiological organization of syllables: a review. J. Phonetics 27, 23\u201354 (1999)","journal-title":"J. Phonetics"},{"key":"962_CR21","unstructured":"P.N. Le, E. Ambikairajah, E.H. Choi, Improvement of vietnamese tone classification using FM and MFCC features, in International Conference on Computing and Communication Technologies, (RIVF\u201909) (2009), pp. 1\u20134"},{"key":"962_CR22","volume-title":"The World Atlas of Language Structures Online","author":"I Maddieson","year":"2013","unstructured":"I. Maddieson, Tone, in The World Atlas of Language Structures Online, ed. by Matthew S. Dryer, Martin Haspelmath (Max Planck Institute for Evolutionary Anthropology, Leipzig, 2013)"},{"key":"962_CR23","doi-asserted-by":"crossref","unstructured":"D. Martinez, E.A. Lleida: Ortega and A. Miguel, prosodic features and formant modeling for an i-vector based Language recognition system, in ICASSP (2013)","DOI":"10.1109\/ICASSP.2013.6638988"},{"issue":"10","key":"962_CR24","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1016\/j.specom.2008.04.010","volume":"50","author":"L Mary","year":"2008","unstructured":"L. Mary, B. Yegnanarayana, Extraction and representation of prosodic features for language and speaker recognition. Speech Commun. 50(10), 782\u2013796 (2008)","journal-title":"Speech Commun."},{"key":"962_CR25","unstructured":"L. Mary, Multilevel implicit features for language and speaker recognition. Ph.D. Dissertation (IIT Madras, 2006)"},{"key":"962_CR26","unstructured":"Y. Muthusamy, R. Cole, B. Oshika, The OGI multi-language telephone speech corpuses, in Proceedings of International Conference Spoken Language Processing (ICSLP) (1992), pp. 895\u2013898"},{"key":"962_CR27","unstructured":"R.W.M. Ng, T. Lee, C.C. Leung, B. Ma, H. Li, Analysis and selection of prosodic features for language identification, in Proc. IALP. (2009), pp. 123\u2013128"},{"key":"962_CR28","unstructured":"P. Pittayaporn, Directionality of tone change, in Proceedings of the 16th International Congress of Phonetic Sciences (Saarland University, Saarbr\u00fccken, 2007), pp. 1421\u20131424"},{"key":"962_CR29","first-page":"1","volume":"3","author":"A Poddar","year":"2017","unstructured":"A. Poddar, M. Sahidullah, G. Saha, Improved i-vector extraction technique for speaker verification with short utterances. Int. J. Speech Technol. 3, 1\u201316 (2017)","journal-title":"Int. J. Speech Technol."},{"key":"962_CR30","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1109\/TASL.2008.2010884","volume":"17","author":"SRM Prasanna","year":"2009","unstructured":"S.R.M. Prasanna, B.V.S. Reddy, P. Krishnamurthy, Vowel onset point detection using source, spectral peaks, and modulation spectrum energies. IEEE Trans. Audio Speech Lang. Process. 17, 556\u2013565 (2009)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"962_CR31","volume-title":"The interaction of stress and tone in standard Chinese: experimental findings and theoretical consequences","author":"C Qu","year":"2012","unstructured":"C. Qu, H. Goad, The interaction of stress and tone in standard Chinese: experimental findings and theoretical consequences (Theory and Practice, Max Planck Institute for Evolutionary Anthropology, Tone, 2012)"},{"issue":"4","key":"962_CR32","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1007\/s10772-013-9198-0","volume":"16","author":"V Ramu Reddy","year":"2013","unstructured":"V. Ramu Reddy, S. Maity, K.S. Rao, Identification of Indian languages using multi-level spectral and prosodic features. Int. J. Speech Technol. 16(4), 489\u2013511 (2013)","journal-title":"Int. J. Speech Technol."},{"issue":"1","key":"962_CR33","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10772-010-9086-9","volume":"14","author":"KS Rao","year":"2011","unstructured":"K.S. Rao, Application of prosody models for developing speech systems in Indian languages. Int. J. Speech Technol. 14(1), 19\u201333 (2011)","journal-title":"Int. J. Speech Technol."},{"issue":"2","key":"962_CR34","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1137\/1026034","volume":"26","author":"RA Redner","year":"1984","unstructured":"R.A. Redner, H.F. Walker, Mixture densities, maximum likelihood and the EM algorithm. SIAM Rev. 26(2), 195\u2013239 (1984)","journal-title":"SIAM Rev."},{"key":"962_CR35","first-page":"634","volume":"8","author":"B Remijsen","year":"2014","unstructured":"B. Remijsen, The study of tone in languages with a quantity contrast. Language Documentation and Conservation. 8, 634\u2013651 (2014)","journal-title":"Language Documentation and Conservation"},{"key":"962_CR36","volume-title":"Gaussian Mixture Models. Encyclopedia of Biometric Recognition","author":"D Reynolds","year":"2008","unstructured":"D. Reynolds, Gaussian Mixture Models. Encyclopedia of Biometric Recognition (Springer, Berlin, 2008)"},{"key":"962_CR37","doi-asserted-by":"crossref","unstructured":"N. Ryant, J. Hong Yuan, M. Liberman, Mandarin tone classification without pitch tracking, in ICASSP (2014)","DOI":"10.1109\/ICASSP.2014.6854527"},{"issue":"3","key":"962_CR38","first-page":"121","volume":"37","author":"P Sarmah","year":"2010","unstructured":"P. Sarmah, C.R. Wiltshire, A preliminary acoustic study of Mizo vowels and tones. J. Acoust. Soc. India 37(3), 121\u2013129 (2010)","journal-title":"J. Acoust. Soc. India"},{"key":"962_CR39","unstructured":"A.K. Singh, A computational phonetic model for Indian language scripts, in Constraints on Spelling Changes. Fifth International Workshop on Writing Systems (Nijmegen, 2006)"},{"key":"962_CR40","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"D Steven","year":"1980","unstructured":"D. Steven, P. Mermelstein, Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust. Speech Signal Process. 28, 357\u2013366 (1980)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"962_CR41","unstructured":"M.N. Stuttle, A Gaussian mixture model spectral representation for speech recognition. Ph.D. Dissertation (University of Cambridge, 2003)"},{"key":"962_CR42","unstructured":"M.J.S. Suresh, S.A. Thorat, Language identification system using MFCC and SDC feature, Language (2018)"},{"key":"962_CR43","volume-title":"Speech Coding and Synthesis","author":"D Talkin","year":"1995","unstructured":"D. Talkin, A robust algorithm for pitch tracking (RAPT), in Speech Coding and Synthesis, ed. by W.B. Klein, K.K. Paliwal (Elsevier, New York, 1995)"},{"key":"962_CR44","unstructured":"L. Wang, E.E. Ambikairajah, H.C. Choi, Automatic tonal and non-tonal language classification and language identification using prosodic information, in International Symposium on Chinese Spoken language Processing. (ISCSLP) (2006), pp. 485\u2013496"},{"key":"962_CR45","doi-asserted-by":"crossref","unstructured":"L. Wang, E. Ambikairajah, H.C. Choi Eric, Automatic language recognition with tonal and non-tonal language pre-classification, in 15th European Signal Processing Conference (2007)","DOI":"10.1109\/ICME.2007.4284659"},{"key":"962_CR46","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1006\/jpho.1999.0086","volume":"27","author":"Y Xu","year":"1999","unstructured":"Y. Xu, \u2018Effects of tone and focus on the formation and alignment of F 0 contours. J. Phonetics 27, 55\u2013105 (1999)","journal-title":"J. Phonetics"},{"key":"962_CR47","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1159\/000028432","volume":"55","author":"Y Xu","year":"1998","unstructured":"Y. Xu, Consistency of tone-syllable alignment across different syllable structures and speaking rates. Phonetica 55, 179\u2013203 (1998)","journal-title":"Phonetica"},{"issue":"4","key":"962_CR48","first-page":"757","volume":"5","author":"Y Xu","year":"2004","unstructured":"Y. Xu, Understanding tone from the perspective of production and perception. Lang. Linguist. 5(4), 757\u2013797 (2004)","journal-title":"Lang. Linguist."},{"key":"962_CR49","volume-title":"Artificial Neural Networks","author":"B Yegnanarayana","year":"2005","unstructured":"B. Yegnanarayana, Artificial Neural Networks (Prentice-Hall of india Private Limited, New Delhi, 2005)"},{"key":"962_CR50","unstructured":"B. Yin, Language identification with language and feature dependency. Ph.D. Dissertation (The University of New South Wales, 2009)"},{"key":"962_CR51","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1002\/9781118584552.ch17","volume-title":"Chinese Linguistics","author":"J Zhang","year":"2014","unstructured":"J. Zhang, Tones, tonal phonology, and tone sandhi, in Chinese Linguistics, ed. by C.-T. James Huang, Y.-H. Audrey Li, A. Simpson (Wiley, Oxford, 2014), pp. 443\u2013464"}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-018-0962-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00034-018-0962-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-018-0962-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:38:19Z","timestamp":1775245099000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00034-018-0962-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,12]]},"references-count":51,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2019,5]]}},"alternative-id":["962"],"URL":"https:\/\/doi.org\/10.1007\/s00034-018-0962-x","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"value":"0278-081X","type":"print"},{"value":"1531-5878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10,12]]},"assertion":[{"value":"20 February 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 October 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 October 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 October 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}