Ключевые слова
Аннотация
In this thesis, the problems of modeling Uzbek language prosodic elements-word stress, phrase intonation, time metrics (tempo), and pauses-in text-to-speech (TTS) systems based on artificial intelligence are reviewed. Since the Uzbek language has an agglutinative structure, the mathematical and linguistic models of integrating the stress system and intonation templates within it into neural networks are analyzed.
Библиографические ссылки
Jumaniyazov, S., & Nasrullaev, N. “ Oʻzbek nutqini sintez qilish tizimlarida lingvistik modullarni shakllantirish muammolari”-. Oʻzbekistonda sunʼiy intellekt va raqamli texnologiyalar jurnali, 2023.
Abdurahmonov, Gʻ.- “Oʻzbek tilining prosodikasi” .-Toshkent: Fan va texnologiya, 2018.
Shen, J., Pang R., Weiss, R. J., et al. “ Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions”. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing , 2018.
Ren, Y., Ruan, Y., Tan, X. “ Fast and High-Quality End-to-End Text to Speech”.-2006.
Kim, J., Kong, J., & Son, J. “Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech (VITS)”. International Conference on Machine Learning (ICML), 2021.
Taylor, P. “Text-to-Speech Synthesis.” Cambridge University Press.-2009.
Toʻxliyev, B., & Shodiyev, Q. “Hozirgi oʻzbek adabiy tili: Fonetika va Morfologiya”. Toshkent: Oʻqituvchi, 2021.
Zen, H., Senior, A., & Schuster, M. “Statistical parametric speech synthesis using deep neural networks”. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, 2013.
Safarov, Sh. “Nutqning intonatsion strukturasi va uning semantik-pragmatik xususiyatlari”. Samarqand: SamDU nashriyoti, 2019.
Wang, Y., Stanton, D., Zhang, Y., et al. Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis. International Conference on Machine Learning (ICML) ,2018.