Switching Linear Dynamical Systems for Speech Recognition

  title={Switching Linear Dynamical Systems for Speech Recognition},
  author={A-V. I. Rosti and Mark J. F. Gales},
This paper describes the application of Rao-Blackwellised Gibbs sampling (RBGS) to speech recognition using switching linear dynamical systems (SLDSs) as the acoustic model. The SLDS is a hybrid of standard hidden Markov models (HMMs) and linear dynamical systems. It is an extension of the stochastic segment model (SSM) where segments are assumed independent. SLDSs explicitly take into account the strong co-articulation present in speech using a Gauss-Markov process in a low dimensional, latent… CONTINUE READING
Highly Cited
This paper has 33 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 22 extracted citations

Similar Papers

Loading similar papers…