next up previous contents
Next: The LP cepstrum Up: Linear Prediction analysis Previous: The lattice filter implementation

The Itakura distance measure

Consider the case where a speech, tex2html_wrap_inline2787, is passed through the linear predictor, a, corresponding to a template. The residual mean squared error, E, is:
eqnarray1115
So can define
eqnarray1177
Or in the autocorrelation case:
eqnarray1199

Let tex2html_wrap_inline3157 be the augmented vector of ``template'' or ``reference'' LP coefficients tex2html_wrap_inline3159 and tex2html_wrap_inline3161 the augmented vector of ``observed'' or ``unknown'' LP coefficients tex2html_wrap_inline3163 then:
eqnarray1215
In the autocorrelation case this can be computed with similar complexity to the Euclidean distance.


eqnarray1225


Speech Vision Robotics group/Tony Robinson