Date Added: Mar 2010
The authors present a simple and efficient feature modeling approach for tracking the pitch of two speakers speaking simultaneously. They model the spectrogram features of single speakers using Gaussian mixture models in combination with the minimum description length model selection criterion. Furthermore, the MIXture MAXimization (MIXMAX) interaction model is employed to yield a probabilistic representation for the mixture of both speakers. Finally, a factorial hidden Markov model is applied for tracking. They demonstrate experimental results on two databases, and show the excellent performance of the proposed method in comparison to a well known multi-pitch tracking algorithm based on correlogram features.