Speech synthesis using neural network

Noor Abbood Jasim, Sarah Abbood, Mohammed Salah


In this paper, we develop a speech learning machine by using Neural-Network. The work is based on a previous work of Neural Network, named Net Talk and compare Net Talk model with Hidden Markov Model (HMM). The work presents simulated result for the simulated neural network to mimic the pronunciation of English vocabulary especially the vowel sounds and the silent pronounced letters.


Speech learning, Neural-Network, Net Talk, Hidden Markov Model (HMM)

Full Text:



Rebai, I., & Benayed, Y. (2013). Arabic Textto Speech Synthesis Based on Neural Networks for MFCC Estimation. Computer and Information Technology, World Congress on (pp. 1-5). Sousse: IEEE.

Karaali, O., Corrigan, G., Massey, N., Miller, C., Schnurr, O., & Mackie, A. (1998). A High Quality Text-to-Speech System Composed of Multiple Neural Networks. Acoustic, Speech, and Signal Processing, IEEE International Conference on (volume 2) (pp. 1237-1240). Seattle, WA: IEEE.

Product Tour: Ersatz Lab. (2014). Retrieved from Ersatz Lab: http://www.ersatzlabs.com/services/

Product Demos. (2013). Retrieved from Voiceware: http://www.voiceware.co.kr/eng/product/product1.ph

Tachibana, R., & Nishimura, M. (2009). Patent No. 20090070115. Omah, NE, USA.

Speech synthesis (SpeechTech TTS). (2015). Retrieved from Speech Technology: http://www.speechtech.cz/en/products/speech-synthesis-tts.html

Lo,W., & Ching, P. (1996). Phone Based Speech Synthesis With Neural Network and Articulatory Control. Spoken Language, Fourth International Conference on (Volume 4) (pp. 2227-2230). Philadelphia, PA: IEEE.

Karaali, O., Corrigan, G., & Gerson, I. (1996). Speech Synthesis with Neural Networks. World Congress on Neural Network (pp. 45-50). San Diego, CA: International Neural Netowork Society.

Sejnowski, T. J., & Rosenberg, C. R. (1987). Parallel networks that learns to pronounce English text. Complex Systems (1), 145-168.

Sejnowski, T. J., & Rosenberg, C. R. (1986). NETTalk: a parallel network that learns to read aloud. Baltimore: Johns Hopkins University.

Xin Wang , Shinji Takaki &Junichi Yamagishi (2016). A Comparative Study of the Performance of HMM, DNN, and RNN based Speech Synthesis Systems Trained on Very Large Speaker-Dependent Corpora. 9th ISCA Speech Synthesis Workshop • September 13 – 15, 2016 • Sunnyvale, CA, USA.

Falaschi A., Giustiniani M., Verola M. (1989). A Hidden Markov Model Approach to Speech Synthesis. Proceedings of Eurospeech 89 (2): 187-190.

Lee K. (1989). Hidden Markov Models: Past, Present, and Future. Proceedings of Eurospeech 89 (1): 148-155.

DOI: https://doi.org/10.23954/osj.v3i1.1257


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Open Science Journal (OSJ) is multidisciplinary Open Access journal. We accept scientifically rigorous research, regardless of novelty. OSJ broad scope provides a platform to publish original research in all areas of sciences, including interdisciplinary and replication studies as well as negative results.