Dr. Jayapradha J, Prof. Ts. Dr. Haw Su Cheng, Dr. Palanichamy Naveen
Description of Invention
Currently, there exist apps and websites that perform live video interviews. However, they still require some resources because everyone still should come online and have an interview. In this work, we proposed the development of an advanced AI-assisted interview system that is designed to streamline the candidate selection process for companies nationwide. This cutting-edge system leverages Artificial Intelligence (AI) for question formulation and facial recognition technology to assess candidate behaviour during interviews. The facial recognition component includes facial capture to identity verification, expression detection to gauge emotional responses, and eye detection for further behavioural analysis. To enhance the interview experience and capture nuanced communication aspects, the Text to Sound (TTS) and Sound to Text (STT) functionalities are integrated. This allows the system to engage in conversations with candidates to simulate the traditional human-resource interview process. The computer describes and vocalizes questions to the candidate, who responds orally. The system then records, transcribes, and analyses the responses, facilitating a comprehensive understanding of the candidate’s qualifications and communication skills. The proposed AI-assisted interview system combines facial recognition, question generation, and advanced audio processing through TTS and STT technologies. This comprehensive approach provides an efficient and objective method for companies to identify and evaluate potential candidates across diverse geographical locations.