5. Speak with Your Application | Learning Microsoft Cognitive Services

Sign In Start Free Trial

Book Overview & Buying
Table Of Contents
Feedback & Rating

Learning Microsoft Cognitive Services

By : Leif Larsen Henning Larsen

Learning Microsoft Cognitive Services

By: Leif Larsen Henning Larsen

Overview of this book

Take your app development to the next level with Learning Microsoft Cognitive Services. Using Leif's knowledge of each of the powerful APIs, you'll learn how to create smarter apps with more human-like capabilities. ? Discover what each API has to offer and learn how to add it to your app ? Study each AI using theory and practical examples ? Learn current API best practices

Preface

Preface

What this book covers

What you need for this book

Who this book is for

Conventions

Reader feedback

Customer support

Free Chapter

1. Getting Started with Microsoft Cognitive Services

1. Getting Started with Microsoft Cognitive Services

Cognitive Services in action for fun and life changing purposes

Setting up boilerplate code

Detecting faces with the Face API

Overview of what we are dealing with

Getting feedback on detected faces

Summary

2. Analyzing Images to Recognize a Face

2. Analyzing Images to Recognize a Face

Learning what an image is about using Computer Vision API

Diving deep into the Face API

Adding identification to our Smart-House application

Summary

3. Analyzing Videos

3. Analyzing Videos

Knowing your mood using the Emotion API

Diving into the Video API

Analyzing emotions in videos

Summary

4. Letting Applications Understand Commands

4. Letting Applications Understand Commands

Creating language-understanding models

Training a model

Executing operations based on commands

Summary

5. Speak with Your Application

5. Speak with Your Application

Converting text to audio and vice versa

Knowing who is speaking

Verifying a person through speech

Customizing speech recognition

Summary

6. Understanding Text

6. Understanding Text

Setting up a common core

Correcting spelling errors

Natural Language Processing using the Web Language Model

Extracting information through textual analysis

Exploring text using linguistic analysis

Summary

7. Extending Knowledge Based on Context

7. Extending Knowledge Based on Context

Linking entities based on context

Providing personalized recommendations

Summary

8. Querying Structured Data in a Natural Way

8. Querying Structured Data in a Natural Way

Tapping into academic content using the Academic API

Creating the backend using the Knowledge Exploration Service

Answering FAQs using QnA Maker

Summary

9. Adding Specialized Searches

9. Adding Specialized Searches

Searching the Web from the Smart-House application

Getting the news

Searching for images and videos

Helping the user with auto suggestions

Search commonalities

Summary

10. Connecting the Pieces

10. Connecting the Pieces

Connecting the pieces

Real-life applications using Microsoft Cognitive Services

Where to go from here

Summary

Appendix A. LUIS Entities and Intents

LUIS pre-built intents

LUIS pre-built entities

Appendix B. Additional Information on Linguistic Analysis

Part-of-Speech Tags

Phrase types

Appendix C. License Information

Appendix C. License Information

Video Frame Analyzer

OpenCvSharp3

Newtonsoft.Json

NAudio

Customer Reviews

5 star

0

4 star

0

3 star

0

2 star

0

1 star

0

Knowing who is speaking

Using the Speaker Recognition API we can identify who is speaking. By defining one or more speaker profiles, with corresponding samples, we can identify if any of these is speaking at any time.

To be able to utilize this feature, we need to go through a few steps:

We add one or more speaker profile to the service.
Each speaker profile enrolls several spoken samples.
We call the service to identify a speaker based on audio input.
Note
If you have not already done so, sign up for an API key for the Speaker Recognition API at https://www.microsoft.com/cognitive-services/en-us/speaker-recognition-api .

Start by adding a new NuGet package to your Smart-House application. Search for and add Microsoft.ProjectOxford.SpeakerRecognition.

Add a new class called SpeakerIdentification to the Model folder of your project. This class will hold all the functionality related to speaker identification.

Beneath the class, we add another class, containing EventArgs for status updates:

    public...

Search

Your notes and bookmarks