logo Idiap Research Institute        
 [BibTeX] [Marc21]
Efficient Kalman Smoothing for Harmonic State-Space Models
Type of publication: Idiap-RR
Citation: barber:rr05-87
Number: Idiap-RR-87-2005
Year: 2005
Institution: IDIAP
Abstract: Harmonic probabilistic models are common in signal analysis. Framed as a linear-Gaussian state-space model, smoothed inference scales as $O(TH^2)$ where $H$ is twice the number of frequencies in the model and $T$ is the length of the time-series. Due to their central role in acoustic modelling, fast effective inference in this model is of some considerable interest. We present a form of `rotation-corrected' low-rank approximation for the backward pass of the Rauch-Tung-Striebel smoother. This provides an effective approximation with computation complexity $O(TSH)$ where $S$ is the rank of the approximation.
Userfields: ipdmembership={learning},
Projects Idiap
Authors Barber, David
Added by: [UNK]
Total mark: 0
  • barber-idiap-rr-05-87.pdf
  • barber-idiap-rr-05-87.ps.gz