Title :
On the applications of the interacting multiple model algorithm for enhancing noisy speech
Author :
Kim, Jae Bum ; Lee, K.Y. ; Lee, C.W.
Author_Institution :
Telecommun. R&D Center, Samsung Electron. Co., South Korea
fDate :
5/1/2000 12:00:00 AM
Abstract :
The interacting multiple model (IMM) algorithm is applied to enhancing speech contaminated by additive white or colored noise. Noisy speech is modeled by a linear state-space model with Markovian switching parameters. The parameters are estimated from the training speech and noise processes. The simulation results shows that the proposed method offers performance gains relative to the previous results with slightly increased complexity
Keywords :
Kalman filters; Markov processes; computational complexity; parameter estimation; recursive estimation; speech enhancement; state-space methods; white noise; Markovian switching parameters; additive white noise; colored noise; interacting multiple model algorithm; linear state-space model; noisy speech; parameter estimation; speech enhancement; Additive noise; Colored noise; Filters; Hidden Markov models; History; Merging; Parameter estimation; Performance gain; Speech enhancement; Speech processing;
Journal_Title :
Speech and Audio Processing, IEEE Transactions on
