Intraview - Virtual Human Interview System

Abstract

Over the years, virtual interview tools have evolved significantly. What started as rigid and unchangeable platforms has now developed into systems that allow people to communicate more naturally, even in remote settings, while helping them build real-world skills. IntraView takes this idea a step further. It is an AI-based interview platform that analyzes a user’s speech and provides feedback on aspects such as clarity, fluency, confidence, pacing, and overall effectiveness of communication. Unlike traditional tools that focus only on whether responses are correct, IntraView also considers behavioral cues such as hesitation, inconsistency, and loss of confidence, all of which play an important role in real interview scenarios. The system is designed for two main user groups. For students, it provides a safe environment where they can practice interviews multiple times, gradually reducing anxiety and improving confidence. It also highlights speaking patterns and communication habits, helping users understand where they need improvement. For organizations, the system offers an improvement over existing AI-based screening tools, which are often limited to text-based evaluation and lack real interaction. By analyzing conversational flow and behavioral patterns, IntraView enables more informed and reliable candidate assessment. The system focuses on speech-based interaction and behavioral evaluation. Currently, it primarily uses audio as the main input, but the architecture allows easy extension to features such as facial expression analysis and customizable interviewer behavior. The primary goal above everything else, is to make the interview process a natural experience. When you concentrate on your genuine method of communication, it not only calms your fears, allows you to gain self-assurance, but also makes preparing for an AI interview really useful.

Introduction

The text discusses the need for an advanced AI-powered interview preparation system called IntraView that helps candidates improve both their technical answers and communication skills. It highlights that in today’s competitive job market, success depends not only on knowledge but also on communication quality, confidence, speech clarity, and behavioral performance, which traditional interview preparation methods fail to properly evaluate.

To address this gap, IntraView provides a realistic, AI-driven mock interview platform. It uses speech-to-text (Whisper) to convert spoken answers into text and a local large language model to generate dynamic interview questions, enabling a natural conversational flow. The system goes beyond correctness of answers and performs behavioral speech analysis, evaluating factors such as tone, pace, hesitation, clarity, and emotional expression to provide detailed feedback.

The platform helps users practice repeatedly in a low-pressure environment, reducing anxiety and improving confidence over time. It also benefits organizations by offering more accurate candidate evaluation based on communication behavior, not just technical responses. Its modular design allows future upgrades such as emotion recognition and advanced performance tracking.

Conclusion

Imagine a platform known as IntraView. The platform makes use of artificial intelligence technology to create simulated job interviews that other practice tools cannot offer. Unlike other platforms, the system is not only able to check whether the answers provided are correct but also to listen keenly. The speech is then converted to text format as the interaction continues. Emotional analysis comes next as the tone, pace, and pauses are considered. The process is therefore more interactive, and the participants feel as if they are having an actual conversation rather than an assessment. The clarity with which the message is conveyed becomes equally important as its content. The integration of different components of artificial intelligence is seen in a particular setting. Since the process involves both interacting and observing at the same time, the individual is able to conduct job interviews repeatedly without losing track of their progress. There is thus continuous feedback on the style of communication, including its fluency, rhythm, and presence. Benefit number one involves the flexibility involved in its construction as it evolves according to recruitment needs, leading to more reliable screening in the first round. It can detect behavioral traits, which other conventional methods ignore, thus making decisions more informed when screening candidates. The most obvious advantage involves improved reliability in conducting these checks due to the ability to pick subtle signs that would be overlooked otherwise The next advantage highlights a new approach in measuring abilities, taking into account the importance of verbal communication. In place of traditional tests, this process involves engaging job applicants through discussion in addition to gathering useful data for analysis purposes. As a result, job candidates are able to improve their communication skills, as well as receive additional feedback on suitability

References

[1] Y. Chou et al., “An AI Mock-interview Platform for Interview Performance Analysis,” IEEE Conference on Smart Computing, pp. 233–240, 2022. [2] S. Kumar and R. Smith, “AI Powered Mock Interview System with Real-Time Voice and Emotion Analysis,” International Journal of Novel Research and Development (IJNRD), vol. 9, no. 2, pp. 210–215, 2024. [3] D. Miller and A. Patrizio, “Using a Virtual Reality Interview Simulator to Explore Factors Affecting Performance,” Virtual Reality Journal (Springer), vol. 29, no. 3, pp. 421–434, 2024. [4] H. Zhang et al., “Advancing Virtual Interviews: AI-Driven Facial Emotion Recognition for Better Recruitment,” IEEE Transactions on Affective Computing, vol. 15, no. 1, pp. 310–320, 2024. [5] J. W. Burgoon et al., “Avatar-Based Feedback in Job Interview Training Impacts Action Identities and Anxiety,” IEEE Transactions on Affective Computing, vol. 15, no. 2, pp. 487–496, 2024. [6] H. Lee and P. Kaur, “Emotional Analysis of Candidates During Online Interviews,” Proceedings of the Conference on Multimedia Systems (CMS), pp. 312–318, 2024. [7] Dr. Prakash S et al., “NexInterview - AI-Driven Mock Interview Preparation Platform,” International Journal of Advanced Research in Science, Communication and Technology (IJARSCT), vol. 5, no. 7, pp. 279–287, 2025. [8] R. K. Verma and M. Singh, “An AI-Driven Approach to Enhance Interview Performance through Voice and Response Analysis,” Journal of Information Systems and Engineering Management (JISEM), vol. 9, no. 3, pp. 78–85, 2025. [9] K. Choi and Y. Lee, “Detection of Emotion Using Multi-Block Deep Learning in a Self-Management Interview App,” Applied Sciences (MDPI), vol. 15, no. 1, pp. 1–14, 2025. [10] R. Silva and E. Pereira, “Speech Emotion Recognition and Serious Games: A Job Interview Simulator Case Study,” Information (MDPI), vol. 16, no. 4, pp. 210–222, 2025. [11] K. R. Prajwal, R. Mukhopadhyay, V. P. Namboodiri, and C. V. Jawahar, “A Lip Sync Expert Is All You Need for Speech to Lip Generation in the Wild,” Proc. ACM MM, 2020. [12] Z. Aldeneh and E. M. Provost, “Using regional saliency for speech emotion recognition,” ICASSP, 2017, pp. 2741–2745. [13] Shashidhar G. Koolagudi and K. S. Rao, “Emotion recognition from speech: A review,” Int. J. Speech Technology, vol. 15, no. 2, pp. 99–117, 2012. [14] Suzhen Wang, “Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion,” https://doi.org/10.24963/ijcai.2021/152 [15] R. Cowie et al., “Emotion recognition in human–computer interaction,” IEEE Signal Processing Magazine, vol. 18, no. 1, pp. 32–80, 2001. [16] Sridevi R, Nithyabharathi S, “Virtual interview simulator: leveraging AI/ML and vision technology,” https://doi.org/10.22214/ijraset.2025.66680 [17] Minu Hwang, Insung Kwack, and Ugun Won, “Web-Based AI Mock Interview System Using ChatGPT with Real-Time Voice Interaction,” Engineering and Technology Journal, vol. 10, no. 10, 2025. [18] Dr. Rais Abdul Hamid Khan, Garima Narendra Khatri, Aarti Ganesh More, and Utkarsha Pramod Mahajan, “AI Interview Preparation Web App,” IJNRD, vol. 10, no. 11, pp. 1–5, 2025. [19] Vijayant Verma, Rana Padwar, Apurwa Chandrakar, Khushi Jaiswal, and Palak Mishra, “AI-Powered Mock Interview System for Automated Skill Assessment,” IJRASET, vol. 13, no. 11, 2025. [20] Y. Chou et al., “An AI mock-interview platform for interview performance analysis,” SMARTCOMP, 2022. [21] Sonu Khapekar, Srishti Bothara et al., “AI powered mock interview system with real-time voice and emotion analysis,” Int. J. of Novel Research and Development, vol. 10. [22] D. Miller and A. Patrizio, “Using a virtual reality interview simulator to explore factors influencing people’s behavior,” Virtual Reality. [23] Rohini Mehta et al., “Advancing virtual interviews: AI-driven facial emotion recognition for better recruitment,” IEEE Trans. Affective Computing, vol. 15, no. 1, pp. 310–320, 2024. [24] J. W. Burgoon et al., “Avatar-based feedback in job interview training impacts action identities and anxiety,” 10.1109/TAFFC.2024.3363835. [25] Eleni Siamtanidou et al., “Speech Emotion Recognition and Serious Games: An Entertaining Approach for Crowdsourcing Annotated Samples,” https://doi.org/10.3390/info16030238

Copyright

Copyright © 2026 Mrs. C. Maheswari , Kasba Sanjit , Nehal Abdul Gani , Borugadda Karthik. This 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.