The connections you create with your users can be made more meaningful and impactful by allowing them to use their face and voice rather than just their mouse and keyboard when using your website. By allowing users to communicate using these methods that come more naturally, you’re not only creating a more authentic and memorable experience but you’re also pulling the user deeper into your narrative.
In this course, we’ll explore what is possible with facial and speech recognition technology on the web. We’ll talk philosophically about when and why you might leverage this type of interaction style, and then dive deep into the tools and techniques that are available. We’ll walk step by step through a fully functional speech, face, and emotion recognition example and break down exactly what’s happening every step of the way.
We’ll cover broad concepts about what tools make this possible, and what role each has in the overall system. Then we’ll examine different types of strategies for accomplishing the type of analysis we want to and the pros and cons of each. We’ll review tools like Tensorflow.js, Face++, Watson, Google Speech, and more.
At the end of this class you’ll not only have a thorough understanding of the landscape of web technology for this type of interaction, but you’ll also be able to create your own experiences from start to finish.
This course is for all levels. Beginners, intermediate students, and professionals will be able to follow the step-by-step structure of the course. Parts of the course will involve writing code, so an understanding of web technology fundamentals will help.
Pre-order. This special price is available as you are buying the course in advance. The course will be available by the end of December. The price will increase as we get closer to the date and once it’s online it will be full price - so register now for a big discount.
(*) The times of the chapters as well as the total duration of the course are approximate and may have some variation
The subtitles are automatically generated, so the quality of the captions may vary.5 sections • 17 lectures • 3 hours
-
Introduction2 lectures 08:00 Mins
-
Who am I03:30 Mins
-
What we’ll be learning04:30 Mins
-
-
The landscape of AI on the web4 lectures 21:00 Mins
-
Client-side and Server-side03:00 Mins
-
Basics of TensorFlow08:00 Mins
-
Overview of available services05:00 Mins
-
Faces, emotions, and speech05:00 Mins
-
-
Setting up the experience5 lectures 1 Hour 20 Mins
-
Overview of the demo project15:00 Mins
-
Camera, image, and microphone capture18:00 Mins
-
Following face position17:00 Mins
-
Animating to emotions18:00 Mins
-
Visual feedback for speech12:00 Mins
-
-
Tapping into AI4 lectures 1 Hour
-
Connecting position data with TensorFlow18:30 Mins
-
Reading emotion with Face++20:00 Mins
-
Leveraging Watson for speech to text17:00 Mins
-
Takeaways on technique and limitations04:30 Mins
-
-
Conclusion2 lectures 17:00 Mins
-
Review key concepts12:00 Mins
-
Next steps and resources to learn more05:00 Mins
-
