I am readin a paper about dialogue modelling and the identification of dialogue acts using prosody. The paper describes 2, maybe three types of model for utilizing the speech signal: a separate, sequential model and EITHER a combined and intergrated model OR a combined model, and an intergrated model. It's not clear.
Is there a difference between a combined model and an intergrated model or should I count those together? If there is a difference, then what is it?