aliasing is: high frequencies masquerading as low frequencies due to undersampling

Nyquist–Shannon sampling theorem

Sample at ≥ 2× the highest frequency to avoid aliasing

a low-pass filter does: removes frequencies above a cutoff, keeps slow-varying signal

Low-pass filter: removes frequencies above cutoff, retains slow-varying signal

Bias vs variance: high bias = underfitting, high variance = overfitting

High bias = underfitting, high variance = overfitting

Short-time Fourier transform

STFT divides a signal into shorter segments for analysis

mel-frequency cepstral coefficients (MFCCs) capture: speech features on a perceptual scale

MFCCs capture speech features on a perceptual scale by mimicking human auditory perception

AI content watermarking

AI content watermarking embeds imperceptible signals