Spectrogram-based formant tracking via particle filters

This paper presents a particle-filtering method for estimating formant frequencies of speech signals from spectrograms. First, frequency bands corresponding to the analyzed formants are extracted via a two-step dynamic programming based algorithm. A particle-filtering method is then used to accurately locate formants in every formant areas based on the posterior pdf described by a set of support points with associated weights. Formant trajectories of voiced frames of a group of 81 utterances were manually tracked and labeled, partly for model training and partly for algorithm evaluation. In the experiments, the proposed method obtains average estimation errors of 72, 115, and 113 Hz for the first three formants, respectively, whereas LPC based method induces 118, 172, and 250 Hz deviations. The experimental results show that the formants estimated by the proposed method are quite reliable and the trajectories are more accurate than LPC.