Trigger Word Detection Using Sequence Model

Abstract

            One can utilize trigger words to alert anything which is in resting mode. Along these lines, this point in the sound clasp, is the point at which somebody simply wrapped up the trigger word, for example, “Alexa or Hello Siri, or alright Google”. We found out such a great amount about profound learning, and sequence models, that we can really portray a trigger word framework basically. Also, in the wake of ingesting the information succession, the RNN at that point offers a vector that speaks to the information sentence. We have to prepare another system to enter the arrangement x and yield the succession y by picking the most likely sentence. There are some similarities between the sequence to sequence machine translation model and the language models, but there are some significant differences as well.