• Mr. S.S.Shinde
• Ms. Riya Kapadnis
• Mr. Nayan Bobde
• Ms. Ishwari Bhagwat
• Mr. Soumya Nikumbh

This paper presents an interview decoder system that utilizes a dataset containing questions and their corresponding answers. The system generates random questions in audio format and evaluates the user's input by converting their speech to text. The evaluation process is accomplished using an MLPRegressor model. The interview decoder aims to simulate a real interview scenario, providing users with an interactive experience. By randomly selecting questions from the dataset, the system ensures a diverse range of topics and challenges for the user. The speech-to-text conversion allows users to respond orally, enabling a more natural and engaging interaction. To evaluate the user's input, an MLPRegressor model is employed. This model leverages the power of multilayer perceptron neural networks to predict the suitability of the response based on the provided dataset. By assessing the user's answers, the system offers feedback on their performance, enabling them to improve their interview skills. Overall, the interview decoder project combines audio-based question generation, speech-to-text conversion, and MLPRegressor evaluation to create an effective and immersive interview practice tool.

Interview Decoder

"Interview Decoder", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.k75-k81, May-2023, Available :http://www.jetir.org/papers/JETIR2305A09.pdf

"Interview Decoder", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppk75-k81, May-2023, Available at : http://www.jetir.org/papers/JETIR2305A09.pdf