コンピュータ工学および情報技術ジャーナル

Translation of Speech To Speech Using Cloud-Based Services and Deep-Learning Models

Ajit R Patil*, Kamlesh Patil and Sonal Patil

In the last few decades, with the advent of the internet and social media, a global community has formed and its direct application for an underdeveloped community. Cognitive learning is one of the most sought after research fields which seeks to improve human computer interaction. This paper presents an application for speech to speech translation using a combination of cloud services and state of the art machine learning models. For speech to speech translation, a three phase architecture is investigated which contains cloud based speech to text, speech translation, token extraction, speech synthesis model based on deep neural networks, and a vocoder also based on deep neural networks. Our main focus in this study is creating a robust system for speech to speech language translation and the application of this system.