VoiceShield: Explainable Real-Time Deepfake Speech Detection for Indian Languages
Fraud, impersonation and misinformation are being increasingly leveraged using synthetic speech generated by stateof-the-art speech-to-text and voice conversion systems, but the majority of the detectors are designed for English corpora. This paper introduces an end-to-end VoiceShield system which classifies speech as real or fake for five Indian languages (Hindi, Marathi, Urdu, Kannada and Bengali) using a single multilingual classifier. Audio is standardized to 16 kHz mono, segmented in 4-s chunks with 2-s hop, and transformed to 128-band spectrograms on a log Mel scale, and classified using a compact, 0.39 million parameter convolutional neural network (CNN). By recording-level stratified splitting, leakage of segments does not occur, and by using the Gradient-weighted Class Activation Mapping (Grad-CAM), the time–frequency regions responsible for each decision can be highlighted. The trained network is exported to TorchScript and served using a FastAPI back end which has 2 modes: file upload with per-segment analysis, and WebSocket based real-time monitoring, and a React front end. The curated catalogue covers 10,448 recordings (6,751 real, 3,697 fake). The average time spent on model inference on a CPU is 4.03 ms (99th percentile 6.17 ms) with an interactive budget of 200 ms per 4-s segment. We also describe the evaluation protocol to train the whole corpus and talk about threats to validity, especially the source imbalance between real and fake classes.
Authors
- Tina Agrawal
- Prof. Anirudh Bhagwat
- Pranjali Deshmukh
- Vijaya Choudhary
- Manisha Raut
- Mrunal Mungelwar
- Prof. Vaishali Shende
- Samiksha Kinkar
Institutions
- Raisoni Group of Institutions (IN)
- Artificial Intelligence in Medicine (Canada) (CA)
Publication Details
- Journal
- International Journal for Research in Applied Science and Engineering Technology
- Published
- 2026-11-16
- DOI
- https://doi.org/10.22214/ijraset.2026.85692
- Primary Topic
- Speech Recognition and Synthesis
- Type
- article
- Field-Weighted Citation Impact
- 0.00