I apologize for the delay in getting back to you. Yes, I think this should work well with a standard configuration of OpenEars, except that in order to avoid responding to terms which are outside of your initial language model or grammar (containing “hey siri”) you will probably need to use Rejecto. I would recommend beginning by checking out the tutorial here: https://www.politepix.com/openears/tutorial and selecting “Rejecto: Offline speech recognition which ignores spoken words which aren’t in the vocabulary (paid plugin)” and following the instructions.
Alternately, you can try it with a grammar and see if it does enough of a good job rejecting the speech which is out of the grammar. There is more about grammar construction here: https://www.politepix.com/2014/04/10/openears-1-7-introducing-dynamic-grammar-generation/
Feel free to bring your follow-up questions to me after you’ve tried out the tutorial and/or the grammar approach.