Perceptual Features Based Rapid and Robust Language Identification System for Various Indian Classical Languages

  • A. Revathi
  • C. JeyalakshmiEmail author
  • T. Muruganantham
Conference paper
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 28)


In this paper, we have investigated the development of the robust recognition system to identify the language of the spoken utterance in several classical Indian languages. The ability of the machines to identify the language in which communication takes place globally is a paramount in the current scenario. In this work on VQ clustering based language identification, feature vectors extracted from training speeches are converted into set of language specific clustering models. During testing, features extracted from test speeches are applied to the language specific clustering models and hypothesized language is identified based on minimum of averages corresponding to the model using minimum distance classifier. Clustering technique is evaluated with variations in cluster size and length of the test utterances. Better performance is observed for the cluster size of 64 and 900 test utterances of 2–3 s duration. Noteworthy point to be mentioned is that though the clustering technique is an old technique, it provides 97% as average recognition accuracy, 3.13% as average false acceptance rate and 3.13% as false rejection rate for the testing done on the language specific clustering model with 64 as cluster size. To improve the accuracy, formants are also used as a feature and it is observed that formant frequencies do provide complementary evidence in ensuring better accuracy for some of the languages. Performance of the system is assessed by calculating the identification rate as the one corresponding to the correct identification with respect to either MFPLPC or Formants and the overall average accuracy obtained is 99.4% for clustering model with 32 as cluster size. Experiments are conducted on the database containing speech utterances in seven classical and phonetically rich speaker specific Indian languages such as Bengali, Hindi, Kannada, Malayalam, Marathi, Tamil and Telugu.


Clustering Mel frequency perceptual linear predictive cepstrum (MFPLPC) Language identification (LID) False acceptance rate (FAR) False rejection rate (FRR) Standard deviation (STD) Vector quantization (VQ) 


  1. 1.
    Zissman, M.A.: Automatic identification of telephone speech. Lincolns Lab. J. 8(2), 115–143 (1995)Google Scholar
  2. 2.
    Rao, K.S., Nandi, D.: Language identification—a brief review. Springer briefs in speech technology, pp. 11–30Google Scholar
  3. 3.
    Sadanandam, M., Kamakshiprasad, V., Janaki, V.: Automatic language identification using new features and their weightage. Int. J. Adv. Comput. 35(7), 380–385 (2012)Google Scholar
  4. 4.
    Suo, H., Li, M., Lu, P., Yan, Y.: Automatic language identification with discriminative language characterization based on SVM. IEICE Trans. Info. Sys. 91(3), 567–575 (2008)Google Scholar
  5. 5.
    Rajasekar, S.: An automatic language identification using audio features. IJETAE, Special issues (January 2013)Google Scholar
  6. 6.
    Sadanandam, M., Kamakshiprasad, V., Janaki, V.: DHMM based automatic language identification system. Int. J. Info. Technol. Knowl. Manage. 6(1), 93–97 (2012)Google Scholar
  7. 7.
    Sadanandam, M., Kamakshiprasad, V., Janaki, V.: Text independent language identification using DHMM. IJCA 48(1) (2012)Google Scholar
  8. 8.
    Li, H., Bin, M. Lee, C.-H.: A vector space modelling approach to spoken language identification. IEEE Trans. Audio Speech Lang. Process. 15(8), 271–284 (2007)CrossRefGoogle Scholar
  9. 9.
    Sadanandam, M., Kamakshiprasad, V., Janaki, V.: GMM based language identification system using robust features. Int. J. Speech Technol. 17, 99–105 (2014)CrossRefGoogle Scholar
  10. 10.
    Zissman, Mark A.: Comparison of four approaches to automatic language identification of telephone speech. IEEE Trans. Speech Audio Process. 4(1), 31–44 (1996)CrossRefGoogle Scholar
  11. 11.
    Zhang, W., Li, B.,Qu, D., Wang, B.: Automatic language identification using support vector machines. In: Proceedings of 8th International Conference on signal processing, vol. 1 (2006)Google Scholar
  12. 12.
    Lee, K.A., You, C., Li, H.: Spoken language identification using support vector machine with generative front end. In: Acoustics, IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4153–4156 (2008)Google Scholar
  13. 13.
    Deng, Y., Liu, J.: Automatic language identification using support vector machine and phonetic N gram. In: International Conference on Audio, Language and Image Processing ICALIP, pp. 71–74 (2008)Google Scholar
  14. 14.
    Ziaei, A., Ahadi, S.M., Mirrezaie, S.M., Yeganeh, H.: Spoken language identification using a new sequence kernel-based SVM back-end classifier. In: IEEE International Symposium on Signal Processing and Information Technology, ISSPIT, pp. 324–329 (2008)Google Scholar
  15. 15.
    Verma, V.K., Khanna, N.: Indian language identification using k means clustering and support vector machine. Students Conference on Engineering and Systems (SCES), pp. 1–5 (2013)Google Scholar
  16. 16.
    Nicolai, G., Islam, M.A., Greiner, R.: Native language identification using probabilistic graphical models. In: International Conference on Electrical Information and Communication Technology (EICT), pp. 1–6 (2013)Google Scholar
  17. 17.
    Vyas, G., Dutta, M.K.: An integrated spoken language recognition system using support vector machine. In: Seventh International Conference on Contemporary Computing (IC3), pp. 105–108 (2014)Google Scholar
  18. 18.
    Murty, K.S.R., Yegnanarayana, B.: Combining evidence from residual phase and MFCC features for speaker recognition. IEEE Signal Process. Lett. 13(1), 52–55 (2006)CrossRefGoogle Scholar
  19. 19.
    Han, Z.-Y., Wang, X., Wang, J.: Speech recognition system based on visual features and neural network for persons with speech-impairments. Int. J. Modell. Ident. Control 8(3), 240–247 (2009)Google Scholar
  20. 20.
    Jeyalakshmi, C., Revathi, A., Krishnamurthi, V.: Alphabet model-based short vocabulary speech recognition for the assessment of profoundly deaf and hard of hearing speeches. Int. J. Modell. Ident. Control 23(3), 278–286 (2015)Google Scholar
  21. 21.
    Revathi, A., Venkataramani, Y.: Speaker independent continuous speech and isolated digit recognition using VQ and HMM. In: International Conference on Communications and Signal Processing (ICCSP), IEEE, pp. 198–202 (2011)Google Scholar
  22. 22.
    Hermansky, H., Tsuga, K., Makino, S., Wakita, H.: Perceptually based processing in automatic speech recognition. In: Proceedings on IEEE International Conference on Acoustics, speech and signal processing, Tokyo, vol. 11, pp. 1971–1974 (1986)Google Scholar
  23. 23.
    Hermansky, H., Margon, N., Bayya, A., Kohn, P.: The challenge of Inverse E: the RASTA PLP method. In: Proceedings on Twenty fifth IEEE Asilomar conf. on signals, systems and computers, Pacific Grove, CA, USA, November, vol. 2, pp. 800–804 (1991)Google Scholar
  24. 24.
    Hermansky, Hynek, Morgan, Nelson: RASTA processing of speech. IEEE Trans. Speech Audio Process. 2(4), 578–589 (1994)CrossRefGoogle Scholar
  25. 25.
    Revathi, A., Venkataramani, Y.: Perceptual features based isolated digit and continuous speech recognition using iterative clustering approach. In: First International Conference on Networks and Communications, IEEE, pp. 155–160 (2009)Google Scholar
  26. 26.
    Rabiner, L.R., Juang, B.H.: Fundamentals of Speech Recognition. Prentice Hall, New Jersey (1993)zbMATHGoogle Scholar

Copyright information

© Springer International Publishing AG  2018

Authors and Affiliations

  1. 1.Department of Electronics and Communication Engineering, School of EEESastra UniversityThanjavurIndia
  2. 2.Department of Electronics and Communication EngineeringK. Ramakrishnan College of EngineeringTrichyIndia

Personalised recommendations