Efficient HMM-based estimation of missing features, with applications to packet loss concealment

In this paper, we present efficient HMM-based techniques for estimating missing features. By assuming speech features to be observations of hidden Markov processes, we derive a minimum mean-square error (MMSE) solution. We increase the computational efficiency of HMM-based methods by downsampling underlyingMarkov models, and by enforcing symmetry in transitional probability matrices. When applied to features generally utilized in parametric speech coding, namely line spectral frequencies (LSFs), the proposed methods provide significant improvement over the baseline repetition scheme, in terms of Itakura-Saito distortion and peak SNR.