This course is an introduction to speaker recognition techniques.

Speaker recognition lies in the intersection of audio processing, biometrics, and machine learning, and has various applications. You can find the application of speaker recognition on your smart phones, smart home devices, and various commercial services.

In this course, we will start with an introduction to the history of speaker recognition techniques, to see how it evolved from simple human efforts to modern deep learning based intelligent systems.

We will cover the basics of acoustics, perception, audio processing, signal processing, and feature extraction, so you don't need a background in these domains. We will also have an introduction of popular machine learning approaches, such as Gaussian mixture models, support vector machines, factor analysis, and neural networks.

We will focus on how to build speaker recognition systems based on acoustic features and machine learning models, with an emphasis on modern speaker recognition with deep learning, such as the different options for inference logic, loss function, and neural network topologies.

We will also talk about data processing techniques such as data cleansing, data augmentation, and data fusion.

We included lots of hands-on practices and coding examples for you to really master the topics introduced in this course, and a final project to guide you through building your own speaker recognition system from scratch.

If you are a college student interested in AI or signal processing, or a software engineer, system architect or product manager working with related technologies, then this course is definitely for you!