An Enhanced FFT Algorithm: Framework for Keystrokes Acoustic Emanations Denoising Approach on Real-Time Environment

Abstract

In this digital age, the use of (physical or virtual) keyboard is indispensable as that is the most prevalent way of inputting data into keyboard-related-devices. Naturally, the captured keystrokes acoustic emanations or the audio recording of the keystrokes in real time environments are usually mixed with ambient noises; for examples, uncontrolled student noise, noise from fans, doors and windows, moving cars and the likes. However, to remove or reduce these ambient noises, some techniques which include FFT have been exploited in research because the noise perpetually affect the quality of audio and consequently, affects robust detection and classification of the keys. More so, FFT is considered in this research because is not expensive to obtain and it is nearly error-free measurement in audio suitable for waveform signal that is periodic. However, it is deficient in sparse representation of data, which leads to its poor performance in denoising. Therefore, this research work aims to design an enhanced algorithm for the FFT as an effective denoising framework for smartphones keystrokes acoustic emanations on a real-time scenario. This work is still in progress therefore, the researchers anticipate that upon successfully implementation of the algorithm, the enhanced FFT would perform better than the conventional FFT. The preliminary result shows significant improvement in speed of enhanced FFT over conventional FFT.