• Shravya
• Keerthi SH
• Laxmi V

Generating textual descriptions of images has been an important topic in computer vision and natural language processing. A number of techniques based on deep learning have been proposed on this topic. Several existing technologies can perform image-to-text conversion, including optical character recognition (OCR) systems. These systems utilize computer vision algorithms to identify and extract text from images. Additionally, text-to-speech (TTS) systems can convert textual information into audible speech. On the other hand, text-to-image conversion involves generative models like deep neural networks, which can learn to generate images based on textual descriptions. Our proposed methodology involves converting images into text and speech, as well as converting text into images. This process can have various applications, such as assisting visually impaired individuals in understanding visual content or generating visual representations of textual information. Generative Adversarial Network based text to image generator to generate images. A image captioning method trained on real images to generate the captions. Fliker8k dataset is being used. The results of the models using both qualitative and quantitative analysis on popularly used evaluation metrics. A Text-to-speech synthesizer is an application that converts text into spoken word, by analyzing and processing the text using Natural Language Processing (NLP) and then using Digital Signal Processing (DSP) technology to convert this processed text into synthesized speech representation of the text.

Natural Language Processing, Digital Signal Processing, Image captioning, Speech generation, Generative Adversarial Network.

"Image to Text and Speech Synthesis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.j1-j5, May-2023, Available :http://www.jetir.org/papers/JETIR2305946.pdf

"Image to Text and Speech Synthesis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppj1-j5, May-2023, Available at : http://www.jetir.org/papers/JETIR2305946.pdf