MUMBAI, India, June 22 -- Intellectual Property India has published a patent application (202621049026 A) filed by Moresh Madhukar Mukhedkar; Aparna Mane Deshmukh; Atharva Ashok Lohar; Shreya Shetty; Shweta Koparde; and Vivek Patil on April 17, 2026, for Deepfake Audio Detection Using Deep Learning Techniques.
Inventors include Moresh Madhukar Mukhedkar; Aparna Mane Deshmukh; Atharva Ashok Lohar; Shreya Shetty; Shweta Koparde; and Vivek Patil.
The application for the patent was published on June 12, 2026, under issue no. 24/2026.
Abstract: Deepfake audio has emerged as a serious threat in the digital world, enabling the creation of highly realistic but fake voice recordings. This project presents a system for deepfake audio detection using deep learning techniques. The proposed system analyzes audio signals to distinguish between genuine and artificially generated voices. The process begins with audio preprocessing, including noise reduction and normalization. Important features such as Mel-Frequency Cepstral Coefficients (MFCC), spectrograms, and pitch features are extracted from the audio signal. These features are then fed into deep learning models such as Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) for classification. The system is trained on datasets containing both real and fake audio samples, enabling it to learn distinguishing patterns. The final output classifies the audio as real or deepfake along with a confidence score. The proposed system aims to achieve high accuracy and can be applied in areas such as cybersecurity, media verification, and fraud detection.The results demonstrate that deep learning-based approaches can achieve high accuracy in distinguishing between genuine and manipulated audio, although challenges remain in detecting highly sophisticated deepfakes and ensuring robustness across diverse datasets. The study concludes by emphasizing the need for continuous improvement in detection techniques to keep pace with evolving synthesis methods and highlights the importance of integrating such systems into real-world applications for enhanced digital security.
Disclaimer: Curated by HT Syndication.
