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{191573,
        author = {shiva},
        title = {An Intelligent Framework for Detecting Deepfake Audio Using Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {7175-7182},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=191573},
        abstract = {Abstract—Deep fake audio, generated using advanced artificial intelligence techniques, can closely mimic real human voices and create serious risks for privacy, security, and trust in communication systems. Deep fake audio refers to the audio that is generally synthesized and artificially created that is similar to human audio which leads to the many unethical usage of such audio. Study of such fake audio using Deep Learning is essential in order to avoid many manipulative crimes that may occur which takes advantage of audio. The system employs neural network models to analyze these features and classify audio clips as real or fake. Experiments on benchmark datasets show that the method can identify manipulated audio with high accuracy, illustrating the promise of deep learning for protecting the authenticity of voice-based digital media.},
        keywords = {Deep Fake, Deep learning, Convolutional Neural network, Long Short-Term memory(LSTM), synthesized audio, Mel frequency cepstral coefficients(MFCC).},
        month = {January},
        }