Speech Recognition has been a wide area of research for a long time now. Researchers have been putting a lot of efforts and devised different methods for the same. For Speech Recognition system, speech signal is divided or segmented into some acoustic units like phonemes, syllables and word which will reduces the search space for unwanted signal or noise. This research work aims at developing an Automatic Speech Segmentation algorithm for Punjabi language which segments the signal into syllabes. For Automatic Speech Syllable Segmentation, a proposed technique detects the syllable boundaries using gamma tone filter and oscillator. In this proposed technique, valley picking picks the valley of the signal and gives the onset of the speech signal. Results of proposed technique was compared with the existing method which takes less time. After that Automatic Speech Classification algorithm classifies the signal into two classes either native or non native. For this, system had been trained using Artificial Neural Network (ANN) for estimating the parameter of Native and Non-Native spekers using Mel Frequency Cepstrum Coefficients (MFCCs) for feature extraction. The whole work was performed in Matlab2016a and the results generated as output with high accuracy.

MFCC, ANN, MATLAB, Punjabi language, gamma tone fiter bank and oscillator

[1] Y. Youhao," Research on Speech Recognition Technology and Its Application,"in the proceedings of the 2012 International Conference on Computer Science and Electronics Engineering Research, vol. 6, no. 12, pp. 306-309, 2012.
[2] K. Amino, T. Osanai, “Native vs. non-native accent identification using Japanese spoken telephone numbers,” Speech Communication, vol. 56, no. 1, pp. 70–81, 2014.
[3] M. Wester, C. Mayo, “Accent rating by native and non-native listeners,” in the proceedings of the 2014 ICASSP IEEE International Conference Acoustically Speech Signal Processing, no. i, pp. 7699–7703, 2014.
[4] D. B. Hanchate, M. Nalawade, M. Pawar, V. Pophale, P. K. Maurya,“Vocal Digit Recognition using Artificial Neural Network,” IEEE Journal, vol. 7, no. 10, pp. 88–91, 2010.
[5] L. Bouafif and K. Ouni, “A speech tool software for signal processing applications,” in the proceedings of the 2012 6th International Conference Science Electronics Technology Information Telecommunication SETIT, pp. 788–791, 2012.
[6] E. Sakran, S. M. Abdou, S. E. Hamid, M. Rashwan, “A Review : Automatic Speech Segmentation,” International Journal of Computer Science and Mobile Computing, vol. 6, no. 4, pp. 308–315, 2017.
[7] P. Kumari, D. Shakina Deiv, M. Bhattacharya, “Automatic speech recognition of accented Hindi data,” in the proceedings of the 2014 International Conference on Computation of Power, Energy, Information and Communication(ICCPEIC), pp. 68–76, 2014.
[8] A. Kaur, E. T. Singh, “Segmentation of Continuous Punjabi Speech Signal into Syllables,” World Congress on Engineering and Computer Science, vol. I, pp. 20–23, 2010.
[9] S. P. Panda, A. K. Nayak, “Automatic speech segmentation in syllable centric speech recognition system,” International Journal of Speech Technology, vol. 19, no. 1, pp. 9–18, 2016.
[10] K. Geetha, R. Vadivel, “Syllable Segmentation of Tamil Speech Signals Using Vowel Onset Point and Spectral Transition Measure,” Automatic Control and Computer Sciences, vol. 52, no. 1, pp. 21–25, 2018.
[11] L. Mary, A. P. Antony, “Automatic syllabification of speech signal using short time energy and vowel onset points,” International Journal of Speech Technology, pp. 571– 579, 2018.
[12] S. S. Tirumala, S. R. Shahmiri, A. S. Garhwal, “Speaker Identification feature extraction methods: A Systematic Review”, International Journal of Elsevier, Vol(90),pp. 250-271, 2017.
[13] T. Ozseven, M. Dugenci, “SPeech ACoustic (SPAC): A novel tool for speech feature extraction and classification”, International Journal of Elsevier, 136, pp. 1-8, 2018.
[14] M. R. Gamit, K. Dhameliya, Dr. N. S. Bhatt, “Classification Techniques for Speech Recognition”, International Journal of Emerging Technology and Advanced Engineering, vol. 5, no. 2, pp. 58-63, 2015.
[15] C. P. Bharat, A. A. Desai, “Segmentation of Gujarati words from Continuous spoken Gujarati Speech Signal,” VNSGU Journal of Science and Technology, vol. 4, no. 1, pp. 106-112, 2015.
[16] B. Barhate, D. Sisodiya, R. Deore, “Applications of Speech Recognition: For Programming Languages,” International Journal of Scientific Research in Computer Science and Engineering, vol. 6, no. 1, pp. 6-8, 2018.
[17] Madan, D. Gupta, “Speech Feature Extraction and Classification,” International Journal of Computer Applications, vol. 2, no. 1, pp. 10-15, 2014.
[18] H. K. Soni, “Machine Learning – A New Paradigm of AI,” International Journal Scientific Research in Network Security and Communication, vol. 7, no. 3, pp. 31- 32, 2019.