Microsoft Cognitive Services for Developers: 2 Speech

Course details

Microsoft Cognitive Services opens up artificial intelligence to every developer. Cognitive Services gives us access to powerful AI algorithms that allow our apps to hear, speak, identify, and interpret information using natural methods of communication. This course explores the speech APIs, which are responsible for text translation, text to speech, and speaker recognition. Instructor Sahil Malik shows you how to configure Cognitive Services and use the speech capabilities to translate text, convert text to speech and speech to text, and identify and authenticate multiple speakers. Along the way, he covers various APIs, including Translate Text, Bing Speech, and Speaker Recognition.

Learning objectives
Using the Translate Text API
Getting supported languages
Writing code to translate between languages
Performing text to speech
Setting up speech to text
Writing code for speaker identification

Concepts

0. Introduction

01 - Welcome
02 - What you should know
03 - How to use the exercise files

1. The Basics

04 - Introduction
05 - Set up a Node.js project
06 - Add TypeScript debugging support
07 - Add helper code and debugging

2. Translation Text API

08 - Set up a project
09 - Set up Translate Text API in Azure and update a project
10 - Write code for getting supported languages
11 - Get supported languages running and refactor the code
12 - Get supported languages using an access token
13 - Get supported languages using access token
14 - Get language names
15 - Write code for translating between langauges
16 - Translations between multiple languages
17 - Break apart longer sentences
18 - Translate lots of content using TranslateArray
19 - Get languages for Speak
20 - Performing Text-to-Speech

3. Bing Speech API

21 - Set up a project and register Bing Speech in Azure
22 - Speech to Text
23 - Get an access token for Text-to-Speech
24 - Bing Speech Text-to-Speech

4. Speaker Recognition API

25 - The theory behind speaker recognition
26 - Register speaker recognition API in Azure and update the project
27 - Write business objects
28 - Craft up the structure of identification helper class
29 - Write code to create and delete identification profiles
30 - Write code for enrollment
31 - Write code for speaker identification
32 - Enrolling the first user
33 - Enrolling the second user
34 - Identifying speakers
35 - Delete identification profiles

Conclusion

36 - Next steps