We’re using OpenEars dynamic grammar for phrase recognition. The environment includes constant conversation, most of which is not directed at the app. OpenEars is working really well for utterances directed to the application, but we’re finding OpenEars routinely matches unrelated conversation to phrases in the grammar as well. To address this issue, we’re wondering if Rejecto would be appropriate for dynamic grammar applications. I understand it’s a tall order to expose the app to constant conversation and expect it to properly reject all the unrelated utterances. Just want to get a sense for what’s feasible.
An ideal solution would be one that allows us to use Rejecto for a keyphrase at the start of each grammar, not unlike “Hey Siri” or “OK, Google”, but retains the existing aggressive attempts at matching for the rest of the phrase. I’m guessing that’s not possible, but I figured better to ask the expert and get an authoritative answer than to assume it’s impossible based on my limited knowledge.
Thanks for your time and help.