Comparative Analysis and Development of Voice-based Chatbot System for Differently-abled
Anjali Jain, Pooja Bhati
Abstract
Abstract One technology that improved humans’ lifestyle is a Chatbot System, an AI-based system that conducts people’s conversations. Chatbots are used in a wide range of applications-assistive technologies, customer service, home automation, education, medical bots, entertainment, etc. Such technology could be beneficial to differently-abled for teaching, assistance, etc. But when it comes to people with a slight speech disorder or autism, available chatbot systems aren’t very effective. This paper investigates the existing speech recognition APIs based on WER and CER and tries to improve results by adding a personalized layer for the user. This chatbot system can be embedded with existing technologies-domestic robots, smart mirrors, home automation, medical applications, etc. It will open these technologies to a wide range of audiences. The proposed Chatbot will use the existing speech recognition API and improve the results based on the above performance measures.