Raqamli Transformatsiya va Sun’iy Intellekt
CHUQUR OʻQITISH MODELLARI VA ULARNING TTS TIZIMLARIDAGI OʻRNI
Zenodo DOI: 10.5281/zenodo.20569556
Keywords
Abstract
Ushbu maqolada chuqur oʻqitish modellarining nazariy asoslari hamda ularning matnni nutqqa aylantirish (Text-to-Speech, TTS) tizimlaridagi oʻrni tahlil qilingan. Sun’iy neyron tarmoqlarning matematik asoslari, TTS tizimlarining umumiy arxitekturasi, rekurrent neyron tarmoqlar, Transformer va diqqat mexanizmi asosidagi yondashuvlar koʻrib chiqilgan. Shuningdek, autoregressiv, non-autoregressiv, oqimga asoslangan va generativ qarama-qarshi neyron tarmoqlar asosidagi zamonaviy TTS modellarining ishlash tamoyillari yoritilgan. Nutq sintezida prosodik modellashtirish va koʻp komponentli yoʻqotish funksiyalarining ahamiyati tahlil qilingan. Oʻzbek tilida TTS tizimlarini yaratishda uchraydigan lingvistik va prosodik muammolar hamda ularni hal etishning istiqbolli yoʻnalishlari koʻrsatib berilgan.
References
- HuggingFace. Transformers Documentation. – https://huggingface.co
- van den Oord A., Dieleman S., Zen H., et al. WaveNet: A Generative Model for Raw Audio. – DeepMind, 2016.
- Ho J., Jain A., Abbeel P. Denoising Diffusion Probabilistic Models. – 2020.
- Kim J., Kong J., Son J. VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End TTS. – ICML, 2021.
- Popov V., Vovk I., Gogoryan V., et al. Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech. – 2021.
- Shen J., Pang R., Weiss R.J., et al. Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions. – 2018.
- Kamilov M.M., Musayev M.M. Tabiiy tilni qayta ishlash asoslari. – Toshkent, 2018.
- Vaswani A., Shazeer N., Parmar N. etal. Attention Is All You Need // Neural Information Processing Systems. – 2021.
- Bishop C.M. Pattern Recognition and Machine Learning. – Springer, 2006.
- Ping W., Peng K., Chen J., et al. Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning. – 2018.
- Ren Y., Ruan Y., Tan X., et al. FastSpeech: Fast, Robust and Controllable Text to Speech. – NeurIPS, 2019.
- Wang Y., Skerry-Ryan R., Stanton D. Tacotron: Towards End-to-End Speech Synthesis // Interspeech. – 2022.
- Vaswani A., Shazeer N., Parmar N., et al. Attention Is All You Need. – NeurIPS, 2017.
- Raximov N.O. Axborot texnologiyalari va dasturiy ta’minot. – Toshkent, 2022.
- Baevski A., Zhou H., Mohamed A., Auli M. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. – 2020.
- Wang Y., Skerry-Ryan R., Stanton D., et al. Tacotron: Towards End-to-End Speech Synthesis. – Google, 2017.
- Aripov M.M., Ignatyev N.A. Sun’iy intellekt va ekspert tizimlari. – Toshkent, 2015.
- Jurafsky D., Martin J.H. Speech and Language Processing. – Pearson, 3rd edition.
- Xamdamov Oʻ.R., Mamatov N.S. Nutq texnologiyalari va ularning qoʻllanilishi. – Toshkent, 2020.
- Popov V., Vovk I., Gogoryan V. Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech // ICML. – 2022.
- Goodfellow I., Bengio Y., Courville A. Deep Learning. – MIT Press, 2016.
- OpenAI. GPT-based language models documentation. – 2023.
- Prenger R., Valle R., Catanzaro B. WaveGlow: A Flow-based Generative Network for Speech Synthesis. – 2019.