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{183954,
        author = {Chakrapani Anisetti and Dr. P. Sanyasi Naidu},
        title = {Audio Deepfake Detection using Temporal – Spectral Hybrid Features},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {3},
        pages = {3694-3699},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=183954},
        abstract = {Deepfake audio detection is becoming more important because of the growing misuse of synthetic speech technology in harmful ways. This study suggests a new set of features that combine Linear Frequency Cepstral Coefficients (LFCC), their first and second derivatives, and high-energy features to effectively detect deepfake audio. Using the Fake-or-Real (FoR) dataset, we validated our feature-integration strategy to guarantee consistent spoof-detection performance across various acoustic settings. With accuracies ranging from 70% to 99% on the four FoR subsets, the method demonstrated strong cross-condition generalization. This shows its strength and effectiveness for real-world deepfake audio detection tasks.},
        keywords = {Audio deepfake detection, Handcrafted features, Temporal-spectral hybrid features (TSHF), Fake-or-Real dataset.},
        month = {August},
        }