ACCENTO is an AI-powered backend platform that helps users discover YouTube content by automatically identifying and filtering videos based on spoken accents. The system combines speech processing, natural language analysis, and machine learning to classify audio and make video search more accessible for language learners, educators, and international audiences seeking specific English accents.
Built as a scalable backend service, ACCENTO integrates asynchronous processing, REST APIs, caching, databases, and AI inference pipelines to efficiently analyze multimedia content. The project demonstrates the application of modern software engineering principles and artificial intelligence to solve real-world problems involving speech understanding, content analysis, and intelligent search.