While staying within the HMM network, the additional state variables can be added to a temporal model.
In Hidden Markov Models (HMMs), the additional variable is typically added to represent the hidden states. In an HMM, you have observed data (e.g., observations or emissions) and hidden states (e.g., underlying causes or states). The additional variable represents these hidden states, which are not directly observable but influence the observed data. This additional variable enables HMMs to model dynamic systems where there’s uncertainty about the underlying state, making them useful in various applications such as speech recognition, natural language processing, and bioinformatics.