Neural networks are machine learning systems that can be used to make predictions and classifications such as speech recognition. Neural networks form the basis of Microsoft's speech technologies that can understand a user's spoken commands, and that generate output using a human-sounding voice. In a short and informal session, Dr. James McCaffrey, from Microsoft Research in Redmond, WA, will give you all the information you need to get up and running with neural networks and programs that perform speech recognition and speech synthesis using the C# language.
You will learn:
- Understand exactly what neural networks are and how they work
- Understand the similarities and differences between the two main Microsoft speech platforms
- How to create C# programs that recognize spoken commands and that generate human-like voice output /