Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{206936,
        author = {B.V.M.Santhosh Kumar and K.Dinesh Manikumar and A.Ajay kumar and B.Devi Sree Prasanth Reddy},
        title = {Comprehensive Interview Performance Evaluation and Feedback System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {2},
        pages = {3422-3429},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206936},
        abstract = {This paper presents an AI-driven system for automated evaluation of candidate performance during technical interviews. Traditional interview assessment relies heavily on manual evaluation by interviewers, which can be subjective, time-consuming, and difficult to scale for large recruitment processes. To address these limitations, we propose a comprehensive interview analysis framework that processes recorded interview audio and generates objective performance scores using modern artificial intelligence techniques. The proposed system first converts interview audio recordings into textual transcripts using a speech-to-text model based on the Whisper architecture. The transcribed text is then structured into question–answer pairs through automated extraction techniques. These structured responses are subsequently evaluated using a large language model to assess multiple dimensions of candidate performance, including technical depth, communication clarity, and confidence. A weighted scoring mechanism is applied to compute the final interview score, enabling consistent and transparent evaluation across candidates. To validate the proposed framework, a syn-thetic interview audio dataset was generated and processed through the system. Experimental results demonstrate that the proposed approach can efficiently analyze large volumes of interview data while providing meaningful performance metrics and feedback. The system significantly reduces manual evaluation effort while improving the scalability and consistency of interview assessments.},
        keywords = {Interview evaluation, speech-to-text, Whisper, large language models, automated recruitment, AI-based assessment},
        month = {July},
        }