The technology does exist for end users to create their own unique wake up words and/or speaker verification pass-phrases. If the phrase is known and prepared for in advance, we can typically achieve a higher accuracy. Some care needs to be put into training new or unexpected words to ensure the phrases have sufficient differentiated content that doesn’t frequently occur in real world conversations. Also, there needs to be excellent application design to ensure the templates recorded are of good quality. A bad training recording can really mess things up, and adaptive averaging approaches and good application designs can prevent this. We usually recommend training in quiet and using anywhere.