AI BASED VOICE AUTHENTICATION BANKING SYSTEM
AUTHORS:
Mentor
MS.C.S.Selin Chandra
Affiliation
Department of Computer Science and Information Technology, Vels Institute of Science, Technology and Advanced Studies, Chennai, India
DOI: 
SHARE THIS ARTICLE
CC BY 4.0 License:
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
DOWNLOAD ARTICLE
REVIEW REPORT
CITE THIS ARTICLE
Abstract
This project presents the development of a secure voice authentication system for banking applications using biometric speech recognition technology. The system enables users to perform secure login, registration, and financial transactions using their unique voice patterns instead of traditional passwords. The architecture integrates a frontend developed using Thymeleaf, HTML, CSS, and JavaScript for user interaction and audio recording through microphone access. The backend is built using Spring Boot in Java, which manages REST APIs, authentication logic, user accounts, and banking operations efficiently. A Python-based AI module using Flask processes voice recordings, extracts audio features using Librosa, and converts audio formats using FFmpeg. The extracted voice features are stored in MySQL database and compared during login using Euclidean distance to verify user identity. A threshold-based decision mechanism is used to determine authentication success or failure based on similarity between voice samples. The system also supports secure banking features such as user registration, login, and money transfer using mobile numbers. Overall, the project demonstrates the integration of web technologies, AI-based voice processing, and secure backend systems to build a modern authentication framework for security.
Keywords
Article Information
PUBLICATION DETAILS
Review Type:
Double-Blind Peer Review
License:
CC BY-NC 4.0
Volume/Issue:
Volume 02, Issue 8
Review Rounds:
2
Article Type:
Research Article
Publication Date:
Aug 13 2026
Article Metrics
Article Views
22
PDF Downloads
0
HOW TO CITE
Copy
Pavin.R, S. & Mayarudhran.S, (2026). AI Based Voice Authentication Banking System. International Journal of Science, Strategic Management and Technology, 02(8), 1-9. https://doi.org/10.55041/ijsmt.v2i8.037
Pavin.R, Siva, and Mayarudhran.S. "AI Based Voice Authentication Banking System." International Journal of Science, Strategic Management and Technology, vol. 02, no. 8, 2026, pp. 1-9. doi:https://doi.org/10.55041/ijsmt.v2i8.037.
Pavin.R, Siva, and Mayarudhran.S. "AI Based Voice Authentication Banking System." International Journal of Science, Strategic Management and Technology 02, no. 8 (2026): 1-9. https://doi.org/https://doi.org/10.55041/ijsmt.v2i8.037.
References
- Technical Frameworks and Backend
Spring Boot: The primary Java framework used for building the RESTful banking APIs and managing server-side logic. Reference: Spring Framework Documentation (spring.io).
Flask: The Python micro-framework used to host the AI and audio processing service. Reference: Flask Documentation, Pallets Projects.
MySQL: The relational database management system used for storing user credentials and voice feature vectors. Reference: MySQL Official Reference Manual.
- Audio Processing and AI Libraries
Librosa: The specialized Python library used for audio analysis and extraction of MFCC features. Reference: Librosa: Audio and Music Signal Analysis in Python (librosa.org).
FFmpeg: The multimedia framework used for converting WebM browser recordings into WAV format. Reference: FFmpeg Official Documentation and Command Line Tools.
Euclidean Distance Algorithms: Mathematical foundations used for biometric pattern matching and similarity scoring. Reference: "Pattern Recognition and Machine Learning" by Christopher Bishop.
- Frontend Technologies
Thymeleaf: The Java template engine used for rendering the dynamic banking web pages. Reference: Thymeleaf Official Documentation.
MediaRecorder API: The browser-based JavaScript API used for capturing microphone input. Reference: MDN Web Docs - MediaStream Recording API.
- Academic and Research Resources
Voice Biometrics: Research papers regarding Mel-Frequency Cepstral Coefficients (MFCC) and their reliability in speaker recognition.
Example: "Speaker Identification using MFCC and Vector Quantization" (IEEE Xplore).
Full-Stack Development: Books on integrating heterogeneous systems (Java and Python) via RESTful web services. Example: "Hands-On Microservices with Spring Boot and Cloud" by Magnus Larsson.
- Technical Documentation and Community
GitHub Repositories: Various open-source implementations of signal processing and Spring-Python integration.
Ethics and Compliance
✓ All ethical standards met
This article has undergone plagiarism screening and double-blind peer review. Editorial policies have been followed. Authors retain copyright under CC BY-NC 4.0 license. The research complies with ethical standards and institutional guidelines.
Indexed In
Similar Articles
Physicochemical Status of Coastal Soil and Groundwater and its Socio- Economic Impact: A Case Study of Sankarpur, Chandpur, and Tajpur
(2026)
DOI: 10.55041/ijsmt.v2i3.026
A Study on Patient Experience with Optimum Resource Utilization in Multi Speciality Hospital
(2026)
DOI: 10.55041/ijsmt.v2i3.437
Azole Antifungal Lozenges for Oral Candidiasis: Mechanism, Efficacy, and Emerging Resistance
(2026)
DOI: 10.55041/ijsmt.v2i3.385
Previous Article
