Modified square difference function using fourier series approximation for pitch estimation

Several pitch estimation algorithms both in time domain as well as frequency domain have been proposed by researchers in last few decades. Among them, Square Difference Function (SDF) is one of the popular time-domain pitch detection algorithms. A modified SDF known as YIN is known to give better results. Each pitch detection algorithm has its limitations and error in pitch detection is observed across all algorithms. We specifically address one of the prominent pitch detection errors, known as harmonic errors where the estimated pitch is one of the multiples of the actual pitch. In this paper, we propose a modification to YIN function using Fourier series approximation to reduce harmonic errors. This method gives better estimate of pitch in case of quasi-periodic signals like music due to use of Fourier series coefficients which captures the signal in a better way. We have studied various harmonic signals and analyzed them to find out the cause for such harmonic errors. Then we apply the algorithm on real music signals as well as synthetic signals. Our simulation study shows that the new algorithm leads to an improved pitch estimation method.