Robust F0 Estimation based on a Multichannel Periodicity Function for distant-talking speech

This work addresses the problem of deriving F0 from distant- talking speech signals acquired by a microphone network. The method here proposed exploits the redundancy across the channels by jointly processing the dierent signals. To this purpose, a multi-microphone periodicity function is de- rived from the magnitude spectrum of all the channels. This function allows to estimate F0 reliably, even under rever- berant conditions, without the need of any post-processing or smoothing technique. Experiments, conducted on real data, showed that the proposed frequency-domain algorithm is more suitable than other time-domain based ones.