Creating a diphone inventory

The fijll list of diphone types is called the diphone inventory, and, once that has been determined, we need to find units of such diphones in real speech. Since we are extracting only one unit for each diphone type, we need to make sure that this is in fact a good example for our purposes. We can state three criteria for this. 

We need to extract diphones that will join togetiier well. At any join, we have a left diphone and a right diphone, which share a phoneme. For each phoneme we will have about 40 left diphones and 40 right diphones, and the aim is to extract units of these 80 diphones such that the last frame of all the left diphones is similar acoustically to the first Same of all the right diphones. 

We wish for the diphones to be typical of their type - since we have only one unit of each, it makes sense to avoid outliers. 

---