On the applications of the interacting multiple model algorithm for enhancing noisy speech

The interacting multiple model (IMM) algorithm is applied to enhancing spee ch contaminated by additive white or colored noise, Noisy speech is modeled by a linear state-space model with Markovian switching parameters. The par ameters are estimated from the training speech and noise processes. The sim ulation results show's that the proposed method offers performance gains re lative to the previous results [4] with slightly increased complexity.