EFFECTIVE ARABIC SPEECH SEGMENTATION STRATEGY
DOI:
https://doi.org/10.11113/jt.v77.3709Keywords:
Component speech segmentation, Zero-crossing counts, Signal energy, consonantsAbstract
Speech segmentation is a process to segment speech utterances into small chunks, where each chunk represents a phoneme. The phoneme is an essential unit in any speech which is recognizable. In this paper, a segmentation speech approach was proposed to segment consonant and vowel phonemes from speech utterances of Arabic basic syllables, in order to analyze the consonant production of a group of Malay-speaking normal hearing children and adults. The approach is a combination of zero-crossing counts and signal energy. The zero-crossing counts were used to extract the noise signals, whilst the signal energy was utilized for identifying the speech signals. The spectrogram was used to determine the frequencies with the most intense energy.Â
References
God, A. M. 1999. Speech Processing Using Wavelet Based Algorithms. Ph.D. Thesis, Cairo University.
Alginahi, Yasser M. 2013. A Survey on Arabic Character Segmentation. International Journal on Document Analysis and Recognition (IJDAR). 16(2): 105-126.
Al-Manie, Mohammed A., Mohammed I. Alkanhal, and Mansour M. Al-Ghamdi. 2010. Arabic Speech Segmentation: Automatic Verses Manual Method and Zero Crossing Measurements. Indian Journal of Science and Technology. 3(12): 1134-1138.
Almisreb, Ali Abd, Ahmad Farid Abidin, and Nooritawati Md Tahir. 2013. Segmentation of Arabic Letters Signal using Multiscale Principal Component analysis and Zero-Crossing Rate based on Malay speakers. IEEE International Conference in Control System, Computing and Engineering (ICCSCE). 483-486.
Abushariah, Mohammad Abd-Alrahman Mahmoud, Raja Noor Ainon, Roziati Zainuddin, Moustafa Elshafei, and Othman Omran Khalifa. 2012. Arabic Speaker-Independent Continuous Automatic Speech Recognition Based on a Phonetically Rich and Balanced Speech Corpus. Int. Arab J. Inf. Technol. 9(1): 84-93.
Sarma, Mousmita, and Kandarpa Kumar Sarma. 2014. Phoneme-based Speech Segmentation Using Hybrid Soft Computing Framework. Computational Intelligence and Complexity. New Delhi: Springer.
AL-Haddad, S. A. R., Salina Abdul Samad, Aini Hussein, K. A. Ishak and A. A. Azid et al. 2006. Automatic Segmentation and Labeling for Malay Speech Recognition. Proceedings of the 6th WSEAS International Conference on Signal Processing, Computational Geometry & Artificial Vision, (GAV’ 06), Stevens Point, Wisconsin, USA. 217-221.
Salam, M. S., D. Mohamad and S. H. Salleh. 2010. Speech Segmentation Using Divergence Algorithm with Zero Crossing Property. Proceedings of the 13th International Conference on 13th International Conference on Computer and Information Technology, Dec. 23-25, IEEE Xplore Press, Dhaka. 488-493.
Anwar, M. J., M. M. Awais, S. Masud and S. Shamail. 2006. Automatic Arabic Speech Segmentation System. Int. J. Inform. Technol. 12: 102-111.
Abdul-Kadir, N. A., R. Sudirman and N. M. Safri. 2010. Modelling of the Arabic Plosive Consonants Characteristics Based on Spectrogram. Proceedings of the 4th Asia International Conference on Mathematical/Analytical Modelling and Computer Simulation, May. 26-28, Kota Kinabalu, Malaysia. 282-285. DOI: 10.1109/AMS.2010.63.
Abdul-Kadir, N. A. and R. Sudirman. 2011. Difficulties of Standard Arabic Phonemes Spoken by Non-Arab Primary School Children based on Formant Frequencies. J. Comp. Sci. 7: 1003-1010. DOI: 10.3844/jcssp.2011.1003.1010.
Paul, B. Praat. 2001. A System for Doing Phonetics by Computer. Glot Int. 5: 341-345. http://www.researchgate.net/publication/208032992_Praat_a_system_for_doing_phonetics_by_computer.
Tolba, M. F., T. N. Azmy, A. A. Abdelhamid and M. E. Gadallah. 2005. A Novel Method for Arabic Consonant/Vowel Segmentation Using Wavelet Transform. IJICIS. 5: 353-364.
Downloads
Published
Issue
Section
License
Copyright of articles that appear in Jurnal Teknologi belongs exclusively to Penerbit Universiti Teknologi Malaysia (Penerbit UTM Press). This copyright covers the rights to reproduce the article, including reprints, electronic reproductions, or any other reproductions of similar nature.
