Persian Phoneme and Syllable Recognition using Recurrent Neural Networks for Phonological Awareness Assessment | ||
| Journal of AI and Data Mining | ||
| دوره 10، شماره 1، فروردین 2022، صفحه 117-126 اصل مقاله (1.59 M) | ||
| نوع مقاله: Original/Review Paper | ||
| شناسه دیجیتال (DOI): 10.22044/jadm.2022.11185.2268 | ||
| نویسندگان | ||
| M. Khanzadi1؛ H. Veisi* 1؛ R. Alinaghizade1؛ Z. Soleymani2 | ||
| 1Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran. | ||
| 2Department of Speech Therapy, School of Rehabilitation, Tehran University of Medical Sciences, Tehran, Iran. | ||
| چکیده | ||
| One of the main problems in children with learning difficulties is the weakness of phonological awareness (PA) skills. In this regard, PA tests are used to evaluate this skill. Currently, this assessment is paper-based for the Persian language. To accelerate the process of the assessments and make it engaging for children, we propose a computer-based solution that is a comprehensive Persian phonological awareness assessment system implementing expressive and pointing tasks. For the expressive tasks, the solution is powered by recurrent neural network-based speech recognition systems. To this end, various recognition modules are implemented, including a phoneme recognition system for the phoneme segmentation task, a syllable recognition system for the syllable segmentation task, and a sub-word recognition system for three types of phoneme deletion tasks, including initial, middle, and final phoneme deletion. The recognition systems use bidirectional long short-term memory neural networks to construct acoustic models. To implement the recognition systems, we designed and collected Persian Kid’s Speech Corpus that is the largest in Persian for children’s speech. The accuracy rate for phoneme recognition was 85.5%, and for syllable recognition was 89.4%. The accuracy rates of the initial, middle, and final phoneme deletion were 96.76%, 98.21%, and 95.9%, respectively. | ||
| کلیدواژهها | ||
| Speech Therapy؛ Phonological Awareness Assessment؛ Kid’s Speech Recognition؛ Persian Phoneme and Syllable Recognition؛ Long Short-Term Memory Neural Network | ||
| مراجع | ||
|
[1] Z. Soleymani, "Phonological awareness and effect of reading in 5.5 and 6.5 years old Persian children" Arch. Rehabil., vol. 1, no. 2, pp. 27–35, 2000.
[2] E. Jafari Sadr, “Implementing Computer-Based Phonological Awareness Assessment in Persian,”, M.S. thesis, Dept. Sci. Technol, Tehran Univ, Tehran , 2017.
[3] N. Family, J. Chandlee, M. Franchini, S. Lord, and G. Rheiner, “Lighten up: the acquisition of light verb constructions in Persian" in Proceedings of the 33rd annual Boston University Conference on Language Development, vol. 1, pp. 139–150, 2009.
[4] M. Eslami, J. Sheikhzadegan, Z. Ahmadinia, and R. Bahrami, "Developing Syllable And Diphone Speech Databases For Persian Text-To-Speech Synthesis System" Signal and Data Processing, vol. -, no. 2, pp. 3-12, 2009.
[5] M. Bijankhan, J. Sheikhzadegan, and M. R. Roohani, "Farsdat-The speech database of Farsi spoken language" Proccedings Australian Conference On Speech Science And Technology, vol. 2, pp. 826-830, 1994.
[6] M. Bijankhan, J. Sheykhzadegan, M. R. Roohani, R. Zarrintare, S. Z. Ghasemi, and M. E. Ghasedi, “Tfarsdat-the telephone Farsi speech database,” in speech communication and technology., Geneva of Conf., Europ, 2003, pp. 1525-1528.
[7] M. Dastjerdi and Z. Soleymani, "What is Phonological Awareness?" J. Except. Child., vol. 6, no. 4, pp. 931–954, 2007.
[8] M. Pérez-Pereira, Z. Martínez-López, and L. Maneiro, "Longitudinal relationships between reading abilities, phonological awareness, language abilities and executive functions: Comparison of low risk preterm and full-term children" Front. Psychol., vol. 11, p. 468, 2020.
[9] H. Ahadi, R. Nadarkhani, and M. Ghayoomi, "A Study of Word Reading in Persian-speaking Children With Dyslexia and Normal Ones" J. Mod. Rehabil., vol. 14, no. 4, pp. 207–216, 2020.
[10] C. Ergül, G. Akoğlu, M. Ç. Ö. Akçamuş, E. Demir, B. K. Tülü, and Z. B. Kudret, "Longitudinal Results on Phonological Awareness and Reading Performance of Turkish-Speaking Children by Socioeconomic Status" Egit. ve Bilim, vol. 46, no. 205, 2021.
[11] C. Míguez‐Álvarez, M. Cuevas‐Alonso, and Á. Saavedra, "Relationships Between Phonological Awareness and Reading in Spanish: A Meta‐Analysis" Language Learnimg, pp. 1-46, October 2021.
[12] Z. Arani Kashani and A. Ghorbani, ”Auditory test of phonological awareness skills (ASHA-5) for 5-6 years old Persian speaking children, ” in Setayeshe Hasti, 1 ed. Tehran, Iran, 2010, ch. 1000.
[13] K. L. Carson, “Efficient and effective classroom phonological awareness practices to improve reading achievement”, Ph.D. dissertation, Dept. Philosophy., Canterbury Univ., New Zealand, April 2012.
[14] K. Carson, T. Boustead, and G. Gillon, "Predicting reading outcomes in the classroom using a computer-based phonological awareness screening and monitoring assessment (Com-PASMA)" Int. J. Speech. Lang. Pathol., vol. 16, no. 6, pp. 552–561, 2014.
[15] P. Patel, M. Torppa, M. Aro, U. Richardson, and H. Lyytinen, "Assessing the effectiveness of a game‐based phonics intervention for first and second grade English language learners in India: A randomized controlled trial" J. Comput. Assist. Learn, vol. 38, no. 1, pp. 76-89, February 2021.
[16] F. Fadaei, H. Kalantari Dehaghi, and M. Abdollahzadeh Rafi, "The effect of computer-based method of» sequential display of letters «on quick naming, phonological awareness, accurate and fluid reading of dyslexic elementary students" Technol. Educ. J., vol. 16, no. 1, pp. 59-70.2021.
[17] T. Winn, J. Miller, and W. van Steenbrugge, "The efficacy of a computer program for increasing phonemic awareness and decoding skills in a primary school setting for children with reading difficulties" Aust. J. Teach. Educ., vol. 45, no. 12, pp. 1–23, 2020.
[18] F. Gers, “Long short-term memory in recurrent neural networks”, PhD dissertation., Verlag nicht ermittelbar, 2001.
[19] A. Graves and J. Schmidhuber, "Framewise phoneme classification with bidirectional LSTM and other neural network architectures" Neural networks, vol. 18, no. 5–6, pp. 602–610, 2005.
[20] D. Yu and L. Deng, Automatic Speech Recognition, 1 ed. Springer, London, 2016.
[21] T. N. Sainath, O. Vinyals, A. Senior, and H. Sak, “Convolutional, long short-term memory, fully connected deep neural networks,” in 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), South Brisbane, QLD, Australia, 2015, pp. 4580–4584.
[22] H. Sameti, H. Veisi, M. Bahrani, B. Babaali, and K. Hosseinzadeh, “Nevisa, a persian continuous speech recognition system,” in Computer Conf., Iran, 2008, pp. 485–492.
[23] Z. Ansari and A. Seyyedsalehi, "Deep Modular Neural Networks with Double Spatio-temporal Association Structure for Persian Continuous Speech Recognition" Signal Data Process., vol. 13, no. 1, pp. 39-56., 2016.
[24] M. Daneshvar and H. Veisi, “Persian phoneme recognition using long short-term memory neural network,” in 2016 Eighth International Conference on Information and Knowledge Technology (IKT), Iran, 2016, pp. 111–115.
[25] M. Asadolahzade Kermanshahi and M. M. Homayounpour, "Improving Phoneme Sequence Recognition using Phoneme Duration Information in DNN-HSMM" Journal of AI and Data Mining, vol. 7, no. 1, pp. 137–147, 2019.
[26] S. Bhatt, A. Jain, and A. Dev, "Syllable based Hindi speech recognition" J. Inf. Optim. Sci., vol. 41, no. 6, pp. 1333–1351, 2020.
[27] A. Ganapathiraju, J. Hamaker, J. Picone, M. Ordowski, and G. R. Doddington, "Syllable-based large vocabulary continuous speech recognition" IEEE Trans. speech audio Process., vol. 9, no. 4, pp. 358–366, 2001.
[28] M. M. Azmi, H. Tolba, S. Mahdy, and M. Fashal, “Syllable-based automatic Arabic speech recognition,” in Proceedings of the 7th WSEAS International Conference on Signal Processing, Robotics and Automation, 2008, pp. 246–250.
[29] M. Khanzadi and H. Veisi, “Creating Kid’s Speech Corpus for Phonological Awareness Assessment,” 24th Natl. CSI Comput. Conf., Iran, 2019.
[30] H. Veisi and H. Sameti, "Hidden-Markov-model-based voice activity detector with high speech detection rate for speech enhancement" IET signal Process., vol. 6, no. 1, pp. 54–63, 2012. | ||
|
آمار تعداد مشاهده مقاله: 597 تعداد دریافت فایل اصل مقاله: 693 |
||