اكتشاف شدة عسر التلفظ باستخدام الشبكات العصبية المتكررة والتلافيفية
##plugins.themes.bootstrap3.article.sidebar##
منشور:
Dec 30, 2024
الكلمات المفتاحية:
تصنيف اضطراب التلفظ - - CNN - RNN CRNN -المؤشرات الصوتية - العلاج الآلي للكلام
##plugins.themes.bootstrap3.article.main##
الملخص
يعتمد تشخيص ومراقبة اضطراب التلفظ، وهو اضطراب في الكلام ناجم عن مشاكل عصبية حركية تؤثر على النطق، على تقييم دقيق لدرجة اضطرابه القصوى. عند إنشاء أنظمة آلية لتحديد وتصنيف الكلام عند اضطراب التلفظ، فإن التصنيف الدقيق لدرجة الاضطراب أمر ضروري. باستخدام نماذج الشبكة العصبية، وتحديدًا الشبكات العصبية المتكررة (RNN) والشبكات العصبية التلافيفية (CNN)، تقدم هذه الورقة تحقيقًا شاملاً حول كيفية التمييز بين الأصوات ذات الاضطراب التلفظي بين مجموعة من عينات الاصوات الطبيعية وتصنيف شدة اضطراب التلفظ. من بين السمات المستخدمة في الدراسة، استعملنا جودة الصوت، والمؤشرات النغمية، والبواني الصوتية، ومؤشرات التردد الميلاني (MFCC)، والمنحنيات الطيفية. إن مقارنة قدرة الشبكات التلافيفية والشبكات المتكررة على تحديد الشذوذ في البيانات الطبيعية، بالإضافة إلى النموذج الهجين الذي يجمع بين الشبكات العصبية التلافيفية والشبكات المتكررة (CRNN)، يعتبر هدفنا من هذه الدراسة. قمنا باستغلال قاعدة البيانات Nemours لتقييم أداء نماذجنا للشبكات العصبية. في النهاية لاحظنا نسبة 99.8% التي تحصلنا عليها تعتبر أعلى دقة تصنيف تم تحقيقها باستخدام هذه القاعدة.
##plugins.themes.bootstrap3.article.details##
كيفية الاقتباس
حمزةأ., & عدوج. (2024). اكتشاف شدة عسر التلفظ باستخدام الشبكات العصبية المتكررة والتلافيفية. AL-Lisaniyyat, 30(2), 27-39. استرجع في من https://crstdla.dz/ojs/index.php/allj/article/view/736
القسم
Articles
المراجع
Al-Qatab, B. A., & Mustafa, M. B. (2021). Classification of dysarthric speech according to the severity of impairment: an analysis of acoustic features. IEEE Access, 9, 18183-18194.
Bai, J., Wang, J., & Zhang, X. (2013). A Parameters Optimization Method of v-Support Vector Machine and Its Application in Speech Recognition. J. Comput., 8(1), 113-120..
Deng, L., & Platt, J. (2014, September). Ensemble deep learning for speech recognition. In Proc. interspeech.
Freed, D. B. (2023). Motor speech disorders: diagnosis and. treatment. plural publishing
Hamza, A., Addou, D., & Kheddar, H. (2023, November). Machine learning approaches for automated detection and classification of dysarthria severity. In 2023 2nd International Conference on Electronics, Energy and Measurement (IC2EM) (Vol. 1, pp. 1-6). IEEE.
Hernandez, A., Kim, S., & Chung, M. (2020). Prosody-based measures for automatic severity assessment of dysarthric speech. Applied Sciences, 10(19), 6999.
Joy, N. M., & Umesh, S. (2018). Improving acoustic models in TORGO dysarthric speech database. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 26(3), 637-645.
Kadi, K. L., & Selouani, S. A. (2019). Distinctive auditory-based cues and rhythm metrics to assess the severity level of dysarthria. Signal and Acoustic Modeling for Speech and Communication Disorders, edited by Patil and Amy Neustein, De Gruyter, 205-226.
Kheddar, H., Bouzid, M., & Megías, D. (2019). Pitch and fourier magnitude based steganography for hiding 2.4 kbps melp bitstream. IET Signal Processing, 13(3), 396-407.
Martínez, D., Lleida, E., Green, P., Christensen, H., Ortega, A., & Miguel, A. (2015). Intelligibility assessment and speech recognizer word accuracy rate prediction for dysarthric speakers in a factor analysis subspace. ACM Transactions on Accessible Computing (TACCESS), 6(3), 1-21.
Mazari, A. C., & Kheddar, H. (2023). Deep learning-based analysis of Algerian dialect dataset targeted hate speech, offensive language and cyberbullying. International Journal of Computing and Digital Systems.
Mehrish, A., Majumder, N., Bharadwaj, R., Mihalcea, R., & Poria, S. (2023). A review of deep learning techniques for speech processing. Information Fusion, 99, 101869.
palmer, R., & Enderby, P. (2007). Methods of speech therapy treatment for stable dysarthria: A review. Advances in Speech Language Pathology, 9(2), 140-153
Rudzicz, F. (2010). Articulatory knowledge in the recognition of dysarthric speech. IEEE Transactions on Audio, Speech, and Language Processing, 19(4), 947-960
Salhi, L., & Cherif, A. (2013, April). Selection of pertinent acoustic features for detection of pathological voices. In 2013 5th International Conference on Modeling, Simulation and Applied Optimization (ICMSAO) (pp. 1-6). IEEE.
Schu, G., Janbakhshi, P., & Kodrasi, I. (2023, June). On using the UA-Speech and TORGO databases to validate automatic dysarthric speech classification approaches. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1-5). IEEE.
Seong, W. K., Kim, N. K., Ha, H. K., & Kim, H. K. (2016, December). A discriminative training method incorporating pronunciation variations for dysarthric automatic speech recognition. In 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA) (pp. 1-5). IEEE.
Tu, M., Wisler, A., Berisha, V., & Liss, J. M. (2016). The relationship between perceptual disturbances in dysarthric speech and automatic speech recognition performance. The Journal of the Acoustical Society of America, 140(5), EL416-EL422.
Xiao, Y., & Cho, K. (2016). Efficient character-level document classification by combining convolution and recurrent layers. arXiv preprint arXiv:1602.00367.
Zuo, Z., Shuai, B., Wang, G., Liu, X., Wang, X., Wang, B., & Chen, Y. (2015). Convolutional recurrent neural networks: Learning spatial dependencies for image representation. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops (pp. 18-26).
Bai, J., Wang, J., & Zhang, X. (2013). A Parameters Optimization Method of v-Support Vector Machine and Its Application in Speech Recognition. J. Comput., 8(1), 113-120..
Deng, L., & Platt, J. (2014, September). Ensemble deep learning for speech recognition. In Proc. interspeech.
Freed, D. B. (2023). Motor speech disorders: diagnosis and. treatment. plural publishing
Hamza, A., Addou, D., & Kheddar, H. (2023, November). Machine learning approaches for automated detection and classification of dysarthria severity. In 2023 2nd International Conference on Electronics, Energy and Measurement (IC2EM) (Vol. 1, pp. 1-6). IEEE.
Hernandez, A., Kim, S., & Chung, M. (2020). Prosody-based measures for automatic severity assessment of dysarthric speech. Applied Sciences, 10(19), 6999.
Joy, N. M., & Umesh, S. (2018). Improving acoustic models in TORGO dysarthric speech database. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 26(3), 637-645.
Kadi, K. L., & Selouani, S. A. (2019). Distinctive auditory-based cues and rhythm metrics to assess the severity level of dysarthria. Signal and Acoustic Modeling for Speech and Communication Disorders, edited by Patil and Amy Neustein, De Gruyter, 205-226.
Kheddar, H., Bouzid, M., & Megías, D. (2019). Pitch and fourier magnitude based steganography for hiding 2.4 kbps melp bitstream. IET Signal Processing, 13(3), 396-407.
Martínez, D., Lleida, E., Green, P., Christensen, H., Ortega, A., & Miguel, A. (2015). Intelligibility assessment and speech recognizer word accuracy rate prediction for dysarthric speakers in a factor analysis subspace. ACM Transactions on Accessible Computing (TACCESS), 6(3), 1-21.
Mazari, A. C., & Kheddar, H. (2023). Deep learning-based analysis of Algerian dialect dataset targeted hate speech, offensive language and cyberbullying. International Journal of Computing and Digital Systems.
Mehrish, A., Majumder, N., Bharadwaj, R., Mihalcea, R., & Poria, S. (2023). A review of deep learning techniques for speech processing. Information Fusion, 99, 101869.
palmer, R., & Enderby, P. (2007). Methods of speech therapy treatment for stable dysarthria: A review. Advances in Speech Language Pathology, 9(2), 140-153
Rudzicz, F. (2010). Articulatory knowledge in the recognition of dysarthric speech. IEEE Transactions on Audio, Speech, and Language Processing, 19(4), 947-960
Salhi, L., & Cherif, A. (2013, April). Selection of pertinent acoustic features for detection of pathological voices. In 2013 5th International Conference on Modeling, Simulation and Applied Optimization (ICMSAO) (pp. 1-6). IEEE.
Schu, G., Janbakhshi, P., & Kodrasi, I. (2023, June). On using the UA-Speech and TORGO databases to validate automatic dysarthric speech classification approaches. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1-5). IEEE.
Seong, W. K., Kim, N. K., Ha, H. K., & Kim, H. K. (2016, December). A discriminative training method incorporating pronunciation variations for dysarthric automatic speech recognition. In 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA) (pp. 1-5). IEEE.
Tu, M., Wisler, A., Berisha, V., & Liss, J. M. (2016). The relationship between perceptual disturbances in dysarthric speech and automatic speech recognition performance. The Journal of the Acoustical Society of America, 140(5), EL416-EL422.
Xiao, Y., & Cho, K. (2016). Efficient character-level document classification by combining convolution and recurrent layers. arXiv preprint arXiv:1602.00367.
Zuo, Z., Shuai, B., Wang, G., Liu, X., Wang, X., Wang, B., & Chen, Y. (2015). Convolutional recurrent neural networks: Learning spatial dependencies for image representation. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops (pp. 18-26).