Publication Date: 2023/12/15
Abstract: This research paper introduces a Web App Story Book Converter that incorporates four machine learning models: text summarization, text-to-audio narration with background music, image generation, and keyword extraction. These models are seamlessly integrated into the app's back-end and front-end architecture, aiming to enhance children's reading abilities and foster a love for reading. The text summarization model provides concise and captivating summaries of stories, aiding comprehension, and retention. The text-to-audio narration model converts story texts into engaging audio narratives with carefully curated background music, creating an immersive storytelling experience. The image generation model produces visual representations corresponding to the story, stimulating children's imagination, and bringing the narrative to life. The keyword extraction model identifies and extracts main characters, enabling children to understand story structures and key elements. Through a user-friendly interface, this app promotes reading comprehension, critical thinking, and creativity. The research showcases the effectiveness of integrating machine learning models into a story book converter, demonstrating the potential for technology to enhance traditional reading experiences and cultivate a lifelong love for literature among children.
Keywords: Machine Learning Models, Text Summarization, Text-to-Audio Narration, Image Generation, Keyword Extraction, Immersive Storytelling, Visual Representations.
DOI: https://doi.org/10.5281/zenodo.10390893
PDF: https://ijirst.demo4.arinfotech.co/assets/upload/files/IJISRT23OCT907.pdf
REFERENCES