An Ensemble Learning-Based Bangla Phoneme Recognition System Using LPCC-2 Features

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 695)

Abstract

An array of devices have emerged lately for easing our daily life but one concern has always been towards designing simple user interface (UI) for such devices. A speech-based UI can be a solution to this, considering the fact that it is one of the most spontaneous and natural modes of interaction for most people. The process of identification of words and phrases from voice signals is known as Speech Recognition. Every language encompasses a unique set of atomic sounds termed as Phonemes. It is these sounds which constitute the vocabulary of that language. Speech Recognition in Bangla is a bit complicated task mostly due to the presence of compound characters. In this paper, a Bangla Phoneme Recognition system is proposed to help in the development of a Bangla Speech Recognizer using a new Linear Predictive Cepstral Coefficient-based feature, namely LPCC-2. The system has been tested on a data set of 3710 Bangla Swarabarna (Vowel) Phonemes, and an accuracy of 99.06% has been obtained using Ensemble Learning.

Keywords

Phoneme LPCC-2 Ensemble Learning Mean Standard deviation 

Notes

Acknowledgements

The authors would like to thank the students of West Bengal State University for voluntarily providing the voice samples during data collection.

References

  1. 1.
    Ethnologue. http://www.ethnologue.com (2017). Accessed 1 May 2017
  2. 2.
    Forgie, J.W., Forgie, C.D.: Results obtained from a vowel recognition computer program. J. Acoust. Soc. Am. 31, 1480–1489 (1959)CrossRefGoogle Scholar
  3. 3.
    Pramanik, M., Kido, K.: Bengali speech: formant structures of single vowels and initial vowels of words. Proc. ICASSP 1, 178–181 (1976)Google Scholar
  4. 4.
    Das, B., Mandal, S., Mitra, P.: Bengali speech corpus for continuous automatic speech recognition system. In: 2011 International Conference on Speech Database and Assessments (Oriental COCOSDA), pp. 51–55. IEEE (2011)Google Scholar
  5. 5.
    Eity, Q.N., Banik, M., Lisa, N.J., Hassan, F., Hossain, M.S., Huda, M.N.: Bangla speech recognition using two stage multilayer neural networks. In: Proceeding of the International Conference on Signal and Image Processing (ICSIP), pp. 222–226 (2010)Google Scholar
  6. 6.
    Ahmed, M., Shill, P.C., Islam, K., Mollah, M.A.S., Akhand, M.A.H., Acoustic modeling using deep belief network for Bangla speech recognition. In: Proceeding of the International Conference on Computer and Information Technology (ICCIT), pp. 306–311 (2015)Google Scholar
  7. 7.
    Debnath, S., Saha, S., Aziz, M.T., Sajol, R.H., Rahimi, M.J.: Performance comparison of MFCC based bangla ASR system in presence and absence of third differential coefficients. In: Proceeding of the International Conference on Electrical Engineering and Information Communication Technology (ICEEICT), pp. 1–6 (2016)Google Scholar
  8. 8.
    Sayem, Asm: Speech analysis for alphabets in Bangla language: automatic speech recognition. Int. J. Eng. Res. 3(2), 88–93 (2014)CrossRefGoogle Scholar
  9. 9.
    Hasan, M.M., Hassan, F., Islam, G.M.M., Banik, M., Kotwal, M.R.A., Rahman, S.M.M., Muhammad, G., Mohammad, N.H.: Bangla triphone hmm based word recognition. In: Proceeding of Asia Pacific Conference on Circuits and Systems (APCCAS), pp. 883–886 (2010)Google Scholar
  10. 10.
    Mukherjee, H., Halder, C., Phadikar, S., Roy, K.: READA Bangla phoneme recognition system. In: Proceeding of 5th International Conference on Frontiers in Intelligent Computing: Theory and Applications (FICTA), pp. 599–607 (2017)Google Scholar
  11. 11.
    Hassan, F., Kotwal, M.R.A., Huda, M.N., Bangla phonetic feature table construction for automatic speech recognition. In Proceedings of 16th International Conference on Computer and Information Technology (ICCIT), pp. 51–55 (2013)Google Scholar
  12. 12.
    Kabir, S.M.R., Hassan, F., Ahamed, F., Mamun, K., Huda, M.N., Nusrat, F.: Phonetic features enhancement for Bangla automatic speech recognition. In: Proceeding of the 1st International Conference on Computer and Information Engineering (ICCIE), pp. 25–28 (2015)Google Scholar
  13. 13.
    Audacity, http://www.audacityteam.org/. Accessed 25 April 2017
  14. 14.
    Mukherjee, H., Phadikar, S., Rakshit, P., Roy, K.: REARC—A Bangla Phoneme Recognizer. In: Proceeding of the International Conference on Accessibility to Digital World (ICADW), pp. 177–180 (2016)Google Scholar
  15. 15.
    Rokach, L.: Ensemble-based classifiers. Artif. Intell. Rev. 33, 139 (2010)CrossRefGoogle Scholar
  16. 16.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • Himadri Mukherjee
    • 1
  • Santanu Phadikar
    • 2
  • Kaushik Roy
    • 1
  1. 1.Department of Computer ScienceWest Bengal State UniversityKolkataIndia
  2. 2.Department of Computer Science & EngineeringMaulana Abul Kalam Azad University of TechnologyKolkataIndia

Personalised recommendations