Stephane’s latest post talks about an attempt to use a mathematical algorithm to help decide on which TLDs to allow in the future.
It will be interesting to see how ICANN make use of this tool in the months ahead, but as Black points out, it only deals with visual similarities:
Note that the algorithm is not meant to consider phonetic
similarity. For example, “fish”, “phish”, and “fiche” sound alike, but
are visually distinct and unlikely to be confused.