I'm using the Kevin Murphy's HMM library in MATLAB(http://www.cs.ubc.ca/~murphyk/Software/HMM/hmm.html)
There is a section called 'How to use the toolbox'. There is this example for GMM ouputs:
Let us generate nex=50 vector-valued sequences of length T=50; each vector has size O=2. O = 2; T = 50; nex = 50; data = randn(O,T,nex);
But in my case, The length T of the training sequences is variable. I could solve the problem for the discrete case using cells, but I don't know how to do it here because 'data' is a three-dimensional variable.