Estimation of sinusoids in audio signals using an analysis-by-synthesis neural network

In this paper we present a new method for estimating the frequency, amplitude and phase of sinusoidal components in audio signals. An analysis-by-synthesis system of neural networks is used to extract the sinusoidal parameters from the signal spectrum at each window position of the short-term Fourier transform. The system attempts to find the set of sinusoids that best fits the spectral representation in a least-squares sense. Overcoming a significant limitation of the traditional approach in the art, preliminary detection and interpolation of spectral peaks is not necessary and the method works even when spectral peaks are not well resolved in frequency. This allows for shorter analysis windows and therefore better time resolution of the estimated sinusoidal parameters. Results have also shown robust performance in presence of high levels of additive noise, with signal-to-noise ratios as low as 0 dB