Code covered by the BSD License  

Highlights from
Convert Reflection Coefficients into Prediction Coefficients.

from Convert Reflection Coefficients into Prediction Coefficients. by Nabin S Sharma
Convert reflection coefficients into linear prediction coefficients using Levinson recursion.

rc2lpc(K,varargin)
function A = rc2lpc(K,varargin)
% RC2LPC Convert Reflection Cofficients to Linear Prediction Coefficients.
% A = RC2LPC(K), where K is length P vector of reflection
% coefficients, returns the vector of prediction coefficients of order P 
% linear predictor.
%
% A = RC2LPC(K,'matrix'), where K is length P vector of reflection
% coefficients, returns the (P+1)-by-(P+1) size matrix. This LPC matrix
% consists of LPC vectors of order 0 through P found by using the Levinson 
% recursion.
%
% Nabin Sharma
% April 02, 2009

error(nargchk(1,2,nargin,'struct'));

p = length(K); % Order of linear prediction

len = length(varargin);
switch len
    case 0
        a1 = K(1); % a1(1) = k1
        for i = 2:p
            a = a1;
            for j = 1:(i-1)
                a1(j) = a(j) + K(i)*a(i-j);
            end
            a1(i) = K(i);
        end
        A = [1, a1];
    case 1
        if strcmp(varargin,'matrix')
            A = zeros(p+1,p+1); % initialize the prediction matrix
            A(:,1)=1; % set all a(0) to 1
            A(2,2) = K(1); % set a1(1) = k1
            for i = 2:p
                for j=1:(i-1)
                    A(i+1,j+1)=A(i,j+1)+K(i)*A(i,i-j+1);
                end
                A(i+1,i+1)=K(i);
            end
        else
            error('Check the input arguments.');
        end
end

Contact us at files@mathworks.com