Virtual Assistant for Enhancing English Speaking Skills

Abstract

Over the years with the advent of social media and messaging apps, people have been using jargon, abbreviated words, and casual language while chatting with other people. This leads to a lack of conversational skills during interviews, job meetings, or even daily conversations. Poorly spoken English has been a prime factor due to which students are unsuccessful in clearing the interviews for a job. There are many studies that indicate that an overwhelming percentage of engineers in the country cannot speak English fluently which is required for high-end consulting jobs. Present-day institutions provide solutions for improving English speaking but are expensive. Hence, there is a need for an instantly available conversing partner to hone communication skills. We propose a virtual assistant that can communicate with the user in an attempt to improve English speaking skills. The system consists of SynQG model for question generation, RoBERTa Grammar Error Correction model and praat-parselmouth for speech analysis. The user practices English speaking by answering the questions generated by the system. A thorough speech analysis report is provided to the user based on these answers highlighting mistakes as well as strengths in areas like grammar and pronunciation.