Fundamental frequency estimation by higher order spectrum

This paper proposes a new approach to estimate the fundamental frequency of periodic non-sinusoidal signals by higher order spectrum (HOS). The power of a periodic non-sinusoidal signal is distributed to its fundamental frequency and harmonics. Properly defined higher order spectrum can enhance the fundamental frequency component of spectrum by using the harmonics and therefore has the signal more easily detected from the noise. A specific form of higher order spectrum other than the traditional bispectrum or trispectrum is proposed to improve the reliability of the fundamental frequency estimation for unknown, periodic non-sinusoidal signals. The results of applying the proposed method to weak, high noise signals are surprisingly good. The performances of the various techniques are visually, quantitatively and statistically compared for some signals with different signal-to-noise ratios.