You've now learned so much about deep learning and sequence models that we can actually describe a trigger word system quite simply just on one slide, as you see in this video. But with the rise of speech recognition, that there have been more and more devices you can wake up with your voice and those are sometimes called trigger word detection systems. So let's see how you can build a trigger word system. Examples of trigger word systems include the Amazon Echo, which is woken up with the word Alexa, the Baidu DuerOS powered devices woken up with the phrase xiaodunihao, Apple Siri working up with hey, Siri, and Google Home woken up with okay, Google. So it's thanks to trigger word detection that if you have, say, an Amazon Echo in your living room, you can walk in your living room and just say, Alexa, what time is it? And have it wake up or be triggered by the word Alexa and answer your voice query. So if you can build a trigger word detection system, maybe you can make your computer do something by telling it, computer, activate. One of my friends also worked on turning on and off a particular lamp using a trigger word kind of as a fun project. But what I want to show you is how you can build a trigger word detection system. The literature on trigger detection algorithm is still evolving so there isn't wide consensus yet on what's the best algorithm for trigger word detection. So I'm just going to show you one example of an algorithm you can use. Now, you've seen RNNs like this and what we really do is take an audio clip, maybe compute spectrogram features. And that generates features, x1, x2, x3 audio features, x1, x2, x3 that you pass through an RNN. And so all that remains to be done is to define the target labels. Why? So if this point in the audio clip is when someone just finished saying the trigger word, such as Alexa or xiaodunihao or hey, Siri, or okay, Google, then in the training sets, you can set the target labels to be 0 for everything before that point and right after that to set the target label of 1. And then if a little bit later on, the trigger word was said again and the trigger word was said at this point, then you can again set the target label to be 1 right after that. Now, this type of labelling scheme for an RNN could work. Actually, this will actually work reasonably well. One slight disadvantage of this is it creates a very imbalanced training set to have a lot more 0s than 1s. So one other thing you could do, this is a little bit of a hack, but could make the model a little bit easier to train is instead of setting only a single time step output 1, you can actually make it output a few 1s for several times or for a fixed period of time before reverting back to 0. So and that slightly evens out the ratio of 1s to 0s, but this is a little bit of a hack. But if this is when in the audio clipper the trigger word is said, then right after that, you can set the target label to 1, and if this is the trigger word said again, then right after that is when you want the RNN to output 1. So you get to play more of this as well in the programming exercise. But I think you should feel quite proud of yourself that you've learned enough about deep learning that it just takes one picture and one slide to describe something as complicated as trigger word detection. And based on this, I hope you'll be able to implement something that works and allows you to detect trigger words when you see more of this in the program exercise. In this course on sequence models, you learned about our RNNs, including both GRUs and LSTMs, and then in the second week, you learned a lot about word embeddings and how to learn representations of words. And then in this week, you learned about the attention model as well as how to use it to process audio data. And I hope you have fun implementing all of these ideas in this week's program exercise.