Getting Started With Microsoft Cognitive Services - Bing Speech API

Introduction

In this article, we will learn how to get started with Microsoft Azure Cognitive Services – Bing Speech API.

Overview

This is in continuation of my articles with respect to Cognitive Services. I have come across some complicated articles on Cognitive Services, but as I've been working on this service for the last eight months, I thought of writing simple, step by step articles with respect to Cognitive Services.

If you have landed directly on this article, I would recommend you to read the following -

• Getting started with Microsoft Cognitive Services – Face API
• Getting started with Microsoft Cognitive Services – Emotion API
• Getting started with Microsoft Cognitive Services – LUIS API
• Getting Started With Microsoft Azure Cognitive Services - Recommendations API
• Getting Started With Microsoft Azure Cognitive Services - Speaker Recognition API
• Getting Started With Microsoft Azure Cognitive Services - Text Analytics API
• Getting Started With Microsoft Azure Cognitive Services - Computer Vision API
• Getting Started With Microsoft Azure Cognitive Services – Web Language Model API
• Getting Started With Microsoft Azure Cognitive Services - Bing Autosuggest API
• Getting Started With Microsoft Cognitive Services - Content Moderator API

As defined, Cognitive Services provide the best suite for having interactive, automated models of application. It helps to build powerful intelligence into applications to enable natural and contextual interactions.

Bing Speech API, as described by Microsoft, enables speech capabilities on all internet-connected devices. Every major platform including Android, iOS, Windows, and 3rd party IoT devices are supported. It offers industry-leading speech-to-text, text-to-speech, and language understanding capabilities delivered through the cloud.

Microsoft uses Bing Speech API for Windows applications, like Cortana and Skype Translator as well as Android applications, like Bing Torque for Android Wear and Android Phone.

It offers,

• Speech recognition
  
  
  • Converts spoken audio to text in real time irrespective of any audio source.
  • Supports real-time streaming.
    
    
• Speech intent recognition
  
  
  • Converts spoken audio to intent that drives actions as programmed.
  • Using LUIS models it parses the intent of the speaker to create actions within the application.
    
    
• Text to speech conversion
  
  
  • Converts provided text to spoken audio.
  • It plays an important role when applications need to “talk” to / back to their users.
    Will learn more about Bing Speech APIs in later articles. To start with, let's create cognitive account to Bing Speech using Azure Portal.

Here, let's assume, you have Azure Portal Account. If not, create your free Azure account.

Once done with the account creation, click '+’ => Category, Intelligence + analytics => Services, Cognitive Services APIs.



Fill in the below details.

• Account Name
  Unique name for Cognitive Bing Speech (preview) account.
  
  
• Subscription
  Free; or in case of any subscription you have, must be selected here.
  
  
• API Type
  Cognitive Services provides a set of awesome APIs. For this article we will go with Bing Speech.
  
  
• Pricing Tier
  As per API type selected, pricing option will be listed. Select anyone among the listed options.
  
  
• Resource Group
  Can select existing Resource group or create new.
  
  
  
  
• Account Name
  bingspeechwithkasam.
  
  
• Subscription
  Have selected my subscription.
  
  
• Resource Group
  Selected existing Resource, name AzureDemo
  
  
• API Type
  Bing Speech API.
  
  
  

Pricing Tier

For Bing Speech API type selected, the below pricing options are listed. Let's select Free as pricing tier. You can go with other options available in free trial account.



Click on "Legal Terms" option. A blade with detailed terms will be displayed. Read it carefully and then, click "I Agree" => Create.



After successful creation, the following box could be seen in Dashboard (if you opted to pin it, while creating).



Click on Resource groups => AzureDemo (resource group selected) => Overview Bing Speech API type. The Cognitive account created will be listed. Click on account name.

Overview => Will list all details associated with Bing Speech API type Cognitive account.

Endpoint is base URL of RESTful Bing Speech API provided by Microsoft. Will look into it with deep details in coming articles.



Click on Keys under Resource Management. This will list key details (Key 1, Key 2), which we will be using in our application to leverage Bing Speech API Services.

We can also regenerate the Keys by clicking Regenerate Key option, as shown below.



Click on Quick Start for having quick introduction of Cognitive Services, along with API documentation to use Cognitive Bing Speech API type.



Summary

So, we saw how easy it is to get started with Cognitive Services. By now, we saw how effortlessly we can create Cognitive Services Bing Speech API account using Microsoft Azure Portal. We can use these Keys being generated to allow our app to communicate with super intelligent Bing Speech API offerings.

In later articles, we will use the Keys to look at how they can be used in our application.

I would recommend you try this and be ready with Keys. Happy Azure coding !!!