Recognition of Marathi Isolated Spoken Words Using Interpolation and DTW Techniques

  • Ganesh B. Janvale
  • Vishal Waghmare
  • Vijay Kale
  • Ajit Ghodke
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 248)


This paper contains a Marathi speech database and isolated Marathi spoken words recognition system based on Mel-frequency cepstral coefficient (MFCC), optimal alignment using interpolation and dynamic time warping. Initially, Marathi speech database was designed and developed though Computerized Speech Laboratory. The database contained Marathi isolated words spoken by the 50 speakers including males and females. Mel-frequency Cepstral Coefficients were extracted and used for the recognition purpose. The 100% recognition rate for the isolated words have been achieved for both interpolation and dynamic time warping techniques.


Speech Data base CSL MFCC Speech Recognition and statistical method formatting 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ghadge, S.A., Janvale, G.B., Deshmukh, R.R.: Speech Feature Extraction using Mel – Frequency Cepstral Coefficient (MFCC). In: International Conference on Emerging Trends in Computer Science Communication and Information, January 9-11 (2010)Google Scholar
  2. 2.
    Rbiner, L., Juary, B.-H.: Fundamental of speech Recognition, 1st edn. Pearson Education, Inc., Copyright 1993 AT & T (1993) ISBN 9780130151575Google Scholar
  3. 3.
    Samudravijaya, K., Rao, P.V.S., Agrawal, S.S.: Hindi Speech database. In: Proc. Int. Conf. Spoken Language Processing, ICSLP 2000, Beijing (October 2000)Google Scholar
  4. 4.
  5. 5.
    Lipeika, A., Lipeikience, J., Telkonys, L.: Development of Isolated word speech Recognition system. Information 13(1), 37–46 (2002)MATHGoogle Scholar
  6. 6.
    KayPENTAX.: Multi-speech and Software. Software instrumentation manual, issue G, A division of PENTAX – medical company, Bridgewater line, Lincoln Park, NJ 07035 -1488 USA (February 2007)Google Scholar
  7. 7.
    Janvale, G.B., Gawali, B.W., Deshmukh, S.N., Deshmukh, R.R., Mehrotra, S.C.: Speech Analysis through CSL. on 8th -10th at Inter – University Research Festival. Sant Gadge Baba Amravati University, Amravati (MS) IndiaGoogle Scholar
  8. 8.
    Sato, N., Obuchi, Y.: Emotion Recognition using Mel – Frequency Cepstral Coefficients. Journal of Natural Language processing 14(4), 83–96 (2007)CrossRefGoogle Scholar
  9. 9.
    Keogh, E., Pazzani, M.: Derivative Dynamic Time Warping. In: International Processing of First Intl SIAM International Conference on Data Mining, Chicago, Illinoisi (2001)Google Scholar
  10. 10.
    Kruskall, J., Liberman, M.: The Symmetric Time Warping Problem: From continuous to Discrete. In: Time Warps String Edits and Macromolecules. The Theory and Practice of Sequence Comparison, pp. 125–161. Addison – Wesley Publication Co., Reading Massuchusetts (1983)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Ganesh B. Janvale
    • 1
  • Vishal Waghmare
    • 2
  • Vijay Kale
    • 2
  • Ajit Ghodke
    • 3
  1. 1.Symbiosis Centre for Information TechnologySymbiosis International UniversityPuneIndia
  2. 2.Dept. of CS&ITDr. Babasaheb Ambedkar Marathwada UniversityAurangabadIndia
  3. 3.Sinhgad Institute of Business Administration & Computer Application (SIBACA)LonavalaIndia

Personalised recommendations