CONSTRUCTION OF USAGE DIAGRAMS AND MAIN CLASSES OF SOFTWARE FOR SPEECH-TO-TEXT AND TEXT-TO-SPEECH CONVERSION
Keywords:
Speech recognition, Text-to-speech conversion, Flask, LSTM neural network, MFCC, AJAX, jQuery, Translation algorithm, Spectrogram, API integrationAbstract
This article focuses on the development of software that enables real-time speech-to-text and text-to-speech conversion using web technologies. The backend is implemented using Flask, while the frontend utilizes jQuery and AJAX, allowing users to recognize speech and translate it into other languages. LSTM-based neural networks are applied for speech recognition, analyzing audio data using MFCC features. Additionally, spectral analysis and an encoder-decoder model are used for generating speech from text. The application's interface is simple and intuitive, designed to function on various devices
References
Mamatov, Narzillo & Niyozmatova, N. & Abdullaev, Sh & Samijonov, Abdurashid & Erejepov, K.. (2021). Transformator neyron tarmoqlariga asoslangan nutqni aniqlash. 1-5. 10.1109/ICISCT52966.2021.9670093.
Niyozmatova, N. & Mamatov, Narzillo & Tulaganova, Sh & Samijonov, Abdurashid & Samijonov, B.. (2023). Tanish tizimlarida o‘zbek nutqining nutq faolligini aniqlash usullari. 050019. 10.1063/5.0145438.
Mamatov, N., Niyozmatova, N., Samijonov, A. 2021. Ovozli signallarni oldindan qayta ishlash uchun dasturiy ta'minot. Xalqaro amaliy fanlar va muhandislik jurnali, 18, 2020163. https://doi.org/10.6703/IJASE.202103_18(1).006
Mamatov, N.S., Niyozmatova, N.A., Yoʻldoshev, Y.S., Abdullaev, S.S., Samijonov, A.N. (2023). Diqqat mexanizmiga asoslangan neytral tarmoqda nutqni avtomatik aniqlash. In:
https://medium.com/@swilliam.productions/text-to-speech-with-tacotron-2-573986c42124[online]
Kajetan Malinovski Janette Mandell bilan, Til texnologiyasining kelajagi: Mashina tarjimasining kelajagi. Lionbridge, 2021 yil 22 yanvar
Zaynidinov, H., Singh, M., Tiwary, US, Singh, D. (tahrirlar) Intelligent Human Computer Interaction. IHCI 2022. Kompyuter fanlari bo'yicha ma'ruza matnlari, 13741-jild. Springer, Cham. https://doi.org/10.1007/978-3-031-27199-1_11
NS Mamatov, NA Niyozmatova, AN Samijonov va BN Samijonov, "O'zbek tili uchun til modellari qurilishi", 2022 Xalqaro axborot fanlari va kommunikatsiya texnologiyalari konferentsiyasi (ICISCT), Toshkent, O'zbekiston, 2022, s. 1-4, doi: 10.1109/ICISCT55600.2022.10146788.
Wiedecke, Bernd & Mamatov, Narzillo & Payazov, Mirabbos & Samijonov, Abdurashid. (2019). Akustik signalni tahlil qilish va aniqlash. Innovatsion texnologiyalar va tadqiqot muhandisligi xalqaro jurnali. 8. 2440-2442. 10.35940/ijitee.J9522.0881019.
Narzillo, M., Abdurashid, S., Parakhat, N., & Nilufar, N. (2019). Vektor kvantlash usuliga asoslangan ovoz bilan karnayni avtomatik aniqlash. Innovatsion texnologiyalar va tadqiqot muhandisligi xalqaro jurnali, 8(10), 2443–2445. https://doi.org/10.35940/ijitee.J9523.0881019
Additional Files
Published
How to Cite
License
Copyright (c) 2025 Nurbek Nuritdinov, Narzillo Mamatov

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