CFP last date
20 June 2024
Call for Paper
July Edition
IJCA solicits high quality original research papers for the upcoming July edition of the journal. The last date of research paper submission is 20 June 2024

Submit your paper
Know more
Reseach Article

Effect of Windowing on the Calculation of MFCC Statistical Parameter for Different Gender in Hindi Speech

by Dheeraj Rana, Anurag Jain
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 98 - Number 8
Year of Publication: 2014
Authors: Dheeraj Rana, Anurag Jain
10.5120/17201-7409

Dheeraj Rana, Anurag Jain . Effect of Windowing on the Calculation of MFCC Statistical Parameter for Different Gender in Hindi Speech. International Journal of Computer Applications. 98, 8 ( July 2014), 6-10. DOI=10.5120/17201-7409

@article{ 10.5120/17201-7409,
author = { Dheeraj Rana, Anurag Jain },
title = { Effect of Windowing on the Calculation of MFCC Statistical Parameter for Different Gender in Hindi Speech },
journal = { International Journal of Computer Applications },
issue_date = { July 2014 },
volume = { 98 },
number = { 8 },
month = { July },
year = { 2014 },
issn = { 0975-8887 },
pages = { 6-10 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume98/number8/17201-7409/ },
doi = { 10.5120/17201-7409 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T22:25:39.321967+05:30
%A Dheeraj Rana
%A Anurag Jain
%T Effect of Windowing on the Calculation of MFCC Statistical Parameter for Different Gender in Hindi Speech
%J International Journal of Computer Applications
%@ 0975-8887
%V 98
%N 8
%P 6-10
%D 2014
%I Foundation of Computer Science (FCS), NY, USA
Abstract

This Paper finds the effects of windowing on the values of mean of first 12 MFCC features excluding energy coefficient for different gender. PRAAT software is used for conducting this experiment which uses Hamming windowing technique by default, Standard low values of window and frame size is used as standard for comparison of MFCC values at increased window and frame sizes by computing Average Deviation from standard values. The main aim of carrying out this experiment is to find out whether all 12 basic MFCCs vary uniformly or not when the window size and subsequently frame size are increased. To carry out the experiment, a speech database of 8 speakers (5 males & 3 females) is prepared. Each speaker recorded 15 sentences in two emotional states viz. Natural and Anger. The experiments are performed for 7 different cases of window and frame size.

References
  1. Jain, A. , Prakash,N. and Agrawal, S. S. 2011. Evaluation of MFCC for Emotion Identification in Hindi Speech. In Communication software and Networks (ICCSN) Proceedings, IEEE 3rd International Conference on, May, Xi'an, China.
  2. Sahidullah, Md. and Saha, G. 2012. A Novel Windowing Technique for Efficient Compuation of MFCC for Speaker Recognition. IEEE signal processing letters, vol. 20, no. 2, 2012, pp 149-153.
  3. Kandali, A. B. , Routray, A. and Basu, T. K. 2008. Emotion Recognition from Assamese Speech using MFCC features and GMM classifier In TENCON 2008, IEEE Region 10 Conference, 2008, Hyderabad, India.
  4. Kelly, C. K. and Gobl, C. The Effects of windowing on the calculation of MFCCs for different types of speech sounds. In NOLISP'11 Proceedings 5th international conference on Advances in nonlinear speech processing, Nov, 2011.
  5. Sato, N. and Obuchi, Y. " Emotion Recognition using Mel Frequency Coefficients", Journal of Natural Language Processing, Information and Media Technologies, vol. 2, no. 3, pp. 835-848, September, 2007.
  6. Muda, L. , Begum, M. and Elamvazuthi, I. , "Voice Recognition Algorithms using Mel Frequency Cepstral Coefficient (MFCC) and Dynamic Time Waroing (DTW) Techniques", Journal of Computing, vol. 2, issue 3, pp. 138-143, March, 2010.
  7. Joshi, D. D. and Zalte, M. B. " Recognition of Emotion from Marathi Speech Using MFCC and DWT Algorithms", IJACECT, vol. 2, issue 2, 2013.
  8. Agrawal, S. S. Emotions in Hindi Speech- Analysis, Perception and Recognition. in Speech Database and Assessments. In (Oriental COCOSDA) Proceedings, IEEE International Conference on, October 26-28, 2011, Hsinchu, Taiwan.
  9. Ittichaechareon, C. , Suksri, S. and Thaweesak, " Speech Recognition using MFCC", ICGSM, July 28-29, 2012, Pattaya, Thailand.
  10. Zheng, F. , Zhang, G. and Song, Z. " Comparisons of Different Implementations of MFCC", Journal of Computer Science and Technology, vol. 16, no. 6, pp. 582-589, September, 2011.
  11. Khan, S. , lslam, M. R. and Faizul, M. Automatic Speaker Recognition In 3rd international conference on electrical and computer engineering (ICECE), December 28-30,2004, Dhaka, Bangladesh.
  12. http://practicalcryptography. com/miscellaneous/machine- learning/guide-mel-frequency-cepstral-coefficients-mfccs/
  13. http://www. fon. hum. uva. nl/praat/
Index Terms

Computer Science
Information Sciences

Keywords

MFCC Window size Frame size Hamming Window Mean Average Deviation