Microsoft Cognitive Services for Developers: 2 Speech

Learn how to use Microsoft Cognitive Services to embed AI in your applications. This course covers the speech APIs for text translation, text to speech, and speaker recognition.

Introduction

• Welcome
• What you should know
• How to use the exercise files

1. The Basics

• Introduction
• Set up a Node.js project
• Add TypeScript debugging support
• Add helper code and debugging

2. Translation Text API

• Set up a project
• Set up Translate Text API in Azure and update a project
• Write code for getting supported languages
• Get supported languages running and refactor the code
• Get supported languages using an access token
• Get supported languages using access token
• Get language names
• Write code for translating between langauges
• Translations between multiple languages
• Break apart longer sentences
• Translate lots of content using TranslateArray
• Get languages for Speak
• Performing Text-to-Speech

3. Bing Speech API

• Set up a project and register Bing Speech in Azure
• Speech to Text
• Get an access token for Text-to-Speech
• Bing Speech Text-to-Speech

4. Speaker Recognition API

• The theory behind speaker recognition
• Register speaker recognition API in Azure and update the project
• Write business objects
• Craft up the structure of identification helper class
• Write code to create and delete identification profiles
• Write code for enrollment
• Write code for speaker identification
• Enrolling the first user
• Enrolling the second user
• Identifying speakers
• Delete identification profiles

Conclusion

• Next steps