On 10/24/06, Tobias Bengtsson <[EMAIL PROTECTED]> wrote:
Quick and dirty: make a matrix A whose column are the data (d) delayed by 1, 2, 3... units respectively, then use least squares to solve the equation Ax=d. Durbin-Levinson, nee Levinson, is just an efficient way to do this using knowledge of the special structure of the problem.
Don't know.
Chuck
Hi
I wish to do some Linear Predictive Coding, using durbin-levinson,
covariance, autocorrelation or lattice method algoritms.
However I don't know anything on digital signal processing, neither am I
a star at math.
I've ported http://www.phon.ucl.ac.uk/courses/spsci/dsp/lpc.html to
python, but I couldn't get it to work, that was ported from fortran.
Quick and dirty: make a matrix A whose column are the data (d) delayed by 1, 2, 3... units respectively, then use least squares to solve the equation Ax=d. Durbin-Levinson, nee Levinson, is just an efficient way to do this using knowledge of the special structure of the problem.
Does scipy/numpy contain the means to help me?
Don't know.
Chuck
------------------------------------------------------------------------- Using Tomcat but need to do more? Need to support web services, security? Get stuff done quickly with pre-integrated technology to make your job easier Download IBM WebSphere Application Server v.1.0.1 based on Apache Geronimo http://sel.as-us.falkag.net/sel?cmd=lnk&kid=120709&bid=263057&dat=121642
_______________________________________________ Numpy-discussion mailing list Numpy-discussion@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/numpy-discussion
