Robust formant tracking for continuous speech with speaker variability

Abstract—Several algorithms have been developed for tracking formant frequency trajectories of speech signals, however most of these algorithms are either not robust in real-life noise environ-ments or are not suitable for real-time implementation. The algo-rithm presented in this paper obtains formant frequency estimates from voiced segments of continuous speech by using a time-varying adaptive filterbank to track individual formant frequencies. The formant tracker incorporates an adaptive voicing detector and a gender detector for formant extraction from continuous speech, for both male and female speakers. The algorithm has a low signal delay and provides smooth and accurate estimates for the first four formant frequencies at moderate and high signal-to-noise ratios. Thorough testing of the algorithm has shown that it is robust over a wide range of signal-to-noise ratios for various types of back-ground noises. Index Terms—Formant estimation, hearing aids, speech anal-ysis, speech enhancement. I