Project Abstract

The purpose of this project is to design a smart speaker system that will be particularly helpful for new users in developing nations. These countries are experiencing difficulties in using digital technologies due to a lack of money, a slow internet connection, or an inadequate technology infrastructure. The effort seeks to empower underprivileged communities by developing low-cost devices that are capable of functioning in a large number of languages and do not require a significant amount of internet connectivity. Techniques of iterative development and user-centered design are utilized in order to produce continuous enhancements to the product in response to the input received from consumers. Voice recognition and machine learning techniques are widely adopted around the world. TensorFlow and the Google Speech-to-Text API are two examples of apps that fall under this category. Python and Node.js are two programming languages that can be utilized in the process of developing applications. In order to ensure that the system is suitable for the people who are going to use it, surveys and in-person tests will be conducted with those individuals. This initiative will simplify current activities for a larger number of people and spark a heightened interest in technology. The primary objective of the initiative is to enhance the well-being of the targeted communities by fostering connections with the�?digital�?sphere.

Keywords: internet of things, machine learning, tensor flow

 Conference Details

Session: Presentation Stream 14 at Presentation Slot 5

Location: GH043 at Wednesday 8th 09:00 – 12:30

Markers: Alma Rahat, Deshan Sumanathilaka (GTA)

Course: MSc Advanced Computer Science, Masters PG

Future Plans: I’m looking for work