Does human speech follow Benford's Law?
This addresses the problem of distinguishing human from synthetic speech for applications in audio forensics or security, though it is incremental as it applies an existing law to a new domain.
The paper tackled the problem of whether human speech spectra follow Benford's Law, and found that on average, the frequencies of leading digits in speech magnitude spectra adhere to this distribution, with digits starting with 1 accounting for ~30% and 9 for ~5%, enabling the classification of human vs. synthetic speech.
Researchers have observed that the frequencies of leading digits in many man-made and naturally occurring datasets follow a logarithmic curve, with digits that start with the number 1 accounting for $\sim 30\%$ of all numbers in the dataset and digits that start with the number 9 accounting for $\sim 5\%$ of all numbers in the dataset. This phenomenon, known as Benford's Law, is highly repeatable and appears in lists of numbers from electricity bills, stock prices, tax returns, house prices, death rates, lengths of rivers, and naturally occurring images. In this paper we demonstrate that human speech spectra also follow Benford's Law on average. That is, when averaged over many speakers, the frequencies of leading digits in speech magnitude spectra follow this distribution, although with some variability at the individual sample level. We use this observation to motivate a new set of features that can be efficiently extracted from speech and demonstrate that these features can be used to classify between human speech and synthetic speech.