Artificial Intelligence Driven Gender Based Text-to-Speech System (TTS) Using Deep Learning Algorithms

• DOI: 10.52783/jisem.v10i31s.5123
• Publication Date: 2025-04-09T11:01:25Z
• Authors: Bechoo Lal

Introduction: In this research article the researcher proposed a gender-based Text-to-Speech (TTS) system that uses specific voices to simulate either male or female speech, offering variety of and accents match user's needs. These systems can be integrated into various applications create more natural-sounding, customized speech outputs. The main goal is make synthetic eminently plausible natural sounding, closer human in terms suitability for context sound quality. Objectives: This study aims developed limits TTS technology by using AI; taking account both ethical issues technological constraints must overcome general deployment. ultimate objective are widely accessible, morally acceptable, able mistaken speech. Methods: resrarcher implemented deep neural networks (DNNs), such as recurrent convolution (RNNs), along with recent designs like Transformer Generative Adversarial Networks (GANs). investigates how AI technologies learning particular these obstacles revolutionary way. Implementing assessing cutting edge approaches enhance basis study. It essential employ Results: achieved overall accuracy 85% predictive model based on driven CNN. Perfromance most likely improved fine tuning, adding data training possibly balancing target 50/50 instead 60/40. explores shortcomings conventional systems, especially regard their ability generate understandable. Conclusions: Finally concluded improving text naturalness intelligibility has been an extensive fruitful endeavor, several goals set out do just that. Incorporating contextual situational awareness, intelligibility, prioritizing user centric assessment optimization, ensuring responsible deployment were all stated research. Extensive testing analysis, however, revealed prosody modeling realism. 85%.