ICTACT Journal on Soft Computing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Speaker Identification for Isolated Gujarati Digits using MFCC and VQ


Affiliations
1 Department of Information Technology, G H Patel College of Engineering and Technology, India
     

   Subscribe/Renew Journal


The research presented in this paper is part of an ongoing investigation of speaker identification for Gujarati isolated digit. In our previous work, we evaluated feature extraction method of Gujarati isolated digit for speaker identification using Mel-Frequency Cepstral Coefficient (MFCC). Here we establish on our previous research work for speaker identification of Gujarati isolated digits. The aim of our proposed work is to provide best security or identification to the authentication system which will identify Gujarati speakers. For the projected work we have used MFCC and VQ computation scheme for the Feature extraction and pattern matching techniques. The study also explains about using the technique in brief. For the proposed approach dataset of Gujarati numeral (0 to 10) was recorded from different speakers from different age groups which serve to train and test each speaker speech sample. The distance between each test codeword and each codeword in master codebook is computed. That difference helps in making recognition decision. An experimental evaluation is done using MATLAB simulations. The outcomes indicate that our proposed work of speaker identification system for Gujarati isolated digit achieves good amount of results on our Gujarati digit database with the combination of the proposed technique.

Keywords

Feature Extraction, Isolated Gujarati Digit, MFCC, Speaker Identification, VQ.
Subscription Login to verify subscription
User
Notifications
Font Size

  • H.B. Chauhan and B.A. Tanawala, “Comparative Study of MFCC & LPC Algorithms for Gujarati Isolated Word Recognition”, International Journal of Innovative Research in Computer and Communication Engineering, Vol. 3, No. 2, pp. 1-4, 2012.

  • Parwinder Pal Singh and, Pushpa Rani, “An Approach to Extract Feature using MFCC”, IOSR Journal of Engineering, Vol. 4, No. 8, pp. 21-25, 2014.

  • A. Ghadee Ganesh, B. Jonvale and Ratnadeep.R. Deshmukh, “Speech Feature Extraction Using Mel- Frequency Cepstral Coefficient (MFCC)”, Proceedings of International Conference on Emerging Trends in Computer Science, Communication and Information Technology, pp. 23-28, 2010.

  • A. K. Kumbharana, “Speech Pattern Recognition for Speech to Text Conversion”, Ph.D. Dissertation, Department of Computer Science, Saurashtra University, 2007.

  • M.A. Anusuya and S.K. Katti, “Speech Recognition by Machine: A Review”, International Journal of Computer Science and Information Security, Vol. 6, No. 3, pp. 1-25, 2009.

  • Shall Gujral, Monika Tuteja and Baljit Kaur, “Various Issues In Computerized Speech Recognition Systems”, International Journal of Engineering Research And General Science, Vol. 2, No. 4, pp. 1-6, 2014.

  • Neha Chadha, R.C. Gangwar and Rajeev Bedi, “Current Challenges and Application of Speech Recognition Process using Natural Language Processing: A Survey”, International Journal of Computer Applications, Vol. 131, No. 1, pp. 1-7, 2015.

  • Maruti Limkar, Rama Rao and Vidya Sagvekar, “Isolated Digit Recognition using MFCC & DTW”, International Journal of Advanced Electrical and Electronics Engineering, Vol. 1, No. 1, pp. 59-64, 2012.

  • Therese S Shanthi and S.C. Lingam, “Speaker Based Language Independent Isolated Speech Recognition System”, Proceedings of IEEE International Conference on Communication, Information and Computing Technology, pp. 15-17, 2015.

  • Sarika S. Admuthe and Shubhada Ghugardare, “Survey Paper on Automatic Speaker Recognition Systems”, International Journal of Engineering and Computer Science, Vol. 4, No. 3, pp. 10895-10898, 2015.

  • A. Revathi and Y. Venkataramani, “Speaker Independent Continuous Speech and Isolated Digit Recognition Using VQ & HMM”, Proceedings of International Conference on Communications and Signal Processing, pp. 198-202, 2011.

  • A. Choudhary, R.S. Chauhan and G. Gupta, “Automatic Speech Recognition System for Isolated and Connected Words of Hindi Language By using Hidden Markov Model Toolkit (HTK)”, Proceedings of International Conference on Emerging Trends in Engineering and Technology, pp. 1-7, 2013.

  • S.V. Chapaneri and D.J. Jayaswal, “Efficient Speech Recognition System for Isolated Digits”, International Journal of Computer Science and Engineering Technology, Vol. 4, No. 3, pp. 228-236, 2013.

  • C. Patel Bharat and A. Desai Apurva, “Recognition of Spoken Gujarati Numeral and Its Conversion into Electronic Form”, International Journal of Engineering Research and Technology, Vol. 3, No. 9, pp. 1-5, 2014.

  • D. Gupta, M. Radha, M. Navya and P.B. Manoj. “Isolated Word Speech Recognition using Vector Quantization (VQ)”, International Journal of Advanced Research in Computer Science and Software Engineering, Vol. 2, No. 5, pp. 12-18, 2012.

  • Ch Srinivasa Kumar and P. Mallikarjuna Rao, “Design of an Automatic Speaker Recognition System using MFCC, Vector Quantization and LBG Algorithm”, International Journal on Computer Science and Engineering, Vol. 3, No. 8, pp. 29-42, 2011.

  • Tushar Ratanpara and Narendra Patel, “Singer Identification using Perceptual Features and Cepstral Coefficients of an Audio Signal from Indian Video Songs”, EURASIP Journal on Audio, Speech, and Music Processing, Vol. 16, pp. 1-15, 2015.

  • Lei Lei and She Kun, “Speaker Recognition using Wavelet Cepstral Coefficient, I-Vector, and Cosine Distance Scoring and Its Application for Forensics”, Journal of Electrical and Computer Engineering, Vol. 2016, pp. 1-16, 2016.

  • Kumari Rambha Ranjan, Kartik Mahto, Dipti Kumari and S.S. Solanki, “Singer Identification using MFCC and LPC and its Comparison for ANN and Naive Bayes Classifier”, International Journal of Latest Engineering Research and Applications, Vol. 2, No. 4, pp. 25-30, 2017.

  • M. Mallikarjunan, P.Karmali Radha, K.P. Bharath and Rajesh Kumar Muthu, “Text-Independent Speaker Recognition in Clean and Noisy Backgrounds using Modified VQ-LBG Algorithm”, Circuits, Systems and Signal Processing, pp. 1-18, 2018

  • Kritagya Bhattarai et al., “Experiments on the MFCC Application in Speaker Recognition using Matlab”, Proceedings of IEEE 7th International Conference on Information Science and Technology, pp. 1-7, 2017.

  • Pooja Prajapati and Miral Patel, “Feature Extraction of Isolated Gujarati Digits with Mel Frequency Cepstral Coefficients (MFCCs)”, International Journal of Computer Applications, Vol. 163, No. 6, pp. 29-34, 2017.

  • Safaa Elouahabi, Mohamed Atounti and Mohamed Bellouki, “Amazigh Isolated Word Speech Recognition System using Hidden Markov Model Toolkit (HTK)”, Proceedings of International Conference on Information Technology for Organizations Development, pp. 1-5, 2016.


Abstract Views: 278

PDF Views: 0




  • Speaker Identification for Isolated Gujarati Digits using MFCC and VQ

Abstract Views: 278  |  PDF Views: 0

Authors

Pooja Prajapati
Department of Information Technology, G H Patel College of Engineering and Technology, India
Miral Patel
Department of Information Technology, G H Patel College of Engineering and Technology, India

Abstract


The research presented in this paper is part of an ongoing investigation of speaker identification for Gujarati isolated digit. In our previous work, we evaluated feature extraction method of Gujarati isolated digit for speaker identification using Mel-Frequency Cepstral Coefficient (MFCC). Here we establish on our previous research work for speaker identification of Gujarati isolated digits. The aim of our proposed work is to provide best security or identification to the authentication system which will identify Gujarati speakers. For the projected work we have used MFCC and VQ computation scheme for the Feature extraction and pattern matching techniques. The study also explains about using the technique in brief. For the proposed approach dataset of Gujarati numeral (0 to 10) was recorded from different speakers from different age groups which serve to train and test each speaker speech sample. The distance between each test codeword and each codeword in master codebook is computed. That difference helps in making recognition decision. An experimental evaluation is done using MATLAB simulations. The outcomes indicate that our proposed work of speaker identification system for Gujarati isolated digit achieves good amount of results on our Gujarati digit database with the combination of the proposed technique.

Keywords


Feature Extraction, Isolated Gujarati Digit, MFCC, Speaker Identification, VQ.

References