Tech Dose

Quick Glance At Microsoft Cognitive Services

41 minute read

Lets have quick glance at the Microsoft offering, Cognitive Services.

What are Cognitive Services?

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

Microsoft Cognitive Services provides us the ability to build the apps with powerful algorithms, using a few lines of code. It works across the devices and platforms and with continuous enhancement. It’s easy to set up.

Cognitive Services (preview) comes with a series of APIs, which can be used to enable natural and contextual interaction within your Applications. Cognitive Services offers Language, Speech, Vision, Search and Knowledge APIs.

Language API

The Language API allows apps to process the natural language, evaluate sentiment and topics, and learn how to recognize user needs.

Language Understanding Intelligent Service (LUIS)

LUIS helps an Application to understand commands from the users. The LUIS API, as described by Microsoft is designed to provide you with an easy way to create models, which allows your applications to understand user commands.
For pricing, provisioned regions, and other key details, read Getting Started with Microsoft Cognitive Services — LUIS APIs.

Text Analytics API

This API seamlessly evaluates sentiment and topics to understand the users’  commands. The API, as described by Microsoft, is designed to detect sentiment, key phrases, topics, and language from your text. It is a suite of Text Analytics Web Services built with Azure Machine Learning. No training data is required to use this API; just bring your text data. This API uses the advanced natural language processing techniques to deliver best in class predictions.

For pricing, provisioned regions, and other key details read Getting Started with Microsoft Azure Cognitive Services — Text Analytics API.

Web Language Model API

The Web Language Model API, as described by Microsoft, uses the power of language models trained on Web-scale data. Also, it automates a variety of standard, natural language processing tasks named as state-of-the-art language modeling APIs.

  • Word combination probability
    Calculates the joint probability that a specific word sequence will appear together.
  • Word sequence probability
    Calculates the conditional probability that a particular word will follow a given sequence of words.
  • Predictive text
    Gets a list of words (completions) most likely to follow a given sequence of the words.
  • Word breaking
    Inserts spaces into a string of words that lack spaces, such as a hashtag or a part of a URL.

For pricing, provisioned regions and other key details, read Getting Started with Microsoft Azure Cognitive Services — Web Language Model API.

Bing Spell Check API

The Bing Spell Check API, as described by Microsoft, helps the users to correct spelling errors, recognize the differences among names, brand names and slang, and understand homophones as they type. Also, it detects and corrects the spelling mistakes within your app.

Let’s see some examples of word breaks; in this case, how to correct word-breaking issues with a single flag.

Model API

JSON response is given below.

Model API

As for slang, API easily recognizes an informal language.

Model API

JSON response is given below.

It even provides proofreading capabilities.

Model API

Again, JSON response is given below.

Model API

For pricing, provisioned regions and other key details, read Getting Started with Microsoft Azure Cognitive Services — Bing Spell Check API.

Translator Text API

The Translator Text API, as described by Microsoft, is a Cloud-based automatic translation Service supporting multiple languages. It easily conducts real-time text translation with a simple REST API call. Translator API can be used to build the Applications, Websites, tools or any solution requiring multi-language support.

For pricing, provisioned regions and other key details, read Getting Started with Microsoft Azure Cognitive Services — Translator Text API.

Speech

It’s all about processing the spoken language in your Applications.

Bing Speech API

Bing Speech APIs, as described by Microsoft, enables the speech capabilities on all the Internet-connected devices. Every major platform, including Android, iOS, Windows and third-party IoT devices are supported.

It offers 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 the 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.
    • Plays an important role when the Applications need to “talk” to (or talk back to) their users.

For pricing, provisioned regions and other key details, read Getting Started with Microsoft Azure Cognitive Services — Bing Speech API.

Speaker Recognition API

The Speaker Recognition API, as described by Microsoft, uses speech to identify and authenticate the individual speakers. It gives your app the ability to know who is talking.

Speaker Verification

This is your feature for voice authentication. It verifies the speakers through a simple pass phrase.

Speaker Identification

It identifies the speech with its speaker. It compares the speech from a group of known speakers. It also plays the part of a super intelligent speaker identification tool in our Application.

For pricing, provisioned regions and other key details, read Getting Started with Microsoft Azure Cognitive Services — Speaker Recognition API

Translator Speech API

Translator Speech API, as described by Microsoft, is a Cloud-based automatic translation Service. API enables the developers to add end-to-end, real-time, speech translations to their applications or services. It easily adds speech translation to your app, optimized for real-life conversations.

For pricing, provisioned regions and other key details, read Getting Started with Microsoft Azure Cognitive Services — Translator Speech API.

Vision

Image processing algorithms help you to automate content moderation and build more personalized apps by returning smart insights about faces, images, and emotions.

Face API

Face API, provided by Microsoft Cognitive Services, helps to detect, analyze, and organize the faces in a given image. We can also tag faces in any given photo. It provides the most mature face algorithms to work with, adding super cool intelligence when building the Applications.

For pricing, provisioned regions and other key details, read Getting Started with Microsoft Azure Cognitive Services Face APIs.

Emotion API

Emotion API, as described by Microsoft, creates apps that respond to moods, recognize feelings, and get personal with the users. Using facial expressions, this Cloud-based API can detects happiness, neutrality, sadness, contempt, anger, disgust, fear, and surprise. The artificial intelligence algorithms detect these emotions based on universal facial expressions, functioning even cross-culturally.

For pricing, provisioned regions and other key details, read Getting Started with Microsoft Azure Cognitive Services — Emotion APIs.

Computer Vision API

Computer Vision API, as described by Microsoft, extracts rich information from the images to categorize and process visual data and protect your users from unwanted content. It can:

  • Analyze an image; i.e., getting information about the visual content found in an image.
  • Generate thumbnails: Generate high-quality thumbnails based on any input image.
  • Read text in the images: With Optical Character Recognition (OCR), one can detect text in an image. One can take photos of the text instead of copying to save time and effort.
  • Recognize celebrities: Recognizes 200,000 celebrities from business, politics, sports and entertainment around the world. It is a continuously evolving feature within Computer Vision API.

For pricing, provisioned regions and other key details, read Getting Started with Microsoft Azure Cognitive Services — Computer Vision API.

Content Moderator

Content Moderator, as described by Microsoft, protects your brand and users with an automated image, text and video moderation Services and human review tools.
Powered by intelligent machine learning, Microsoft Content Moderator automatically filters out offensive content in the images, text and video across platforms and includes human review tools for more nuanced cases.

It offers

  • Image moderation API
    • Assess images for offensive and unwanted content.
    • Supports differing file types, including altered images.
    • Includes Optical Character Recognition (OCR).
    • Also includes face detection.
    • Implements fuzzy matching against custom available lists.
  • Text moderation API
    • Detects obscenity in the provided text.
    • Supports more than 100 languages.
    • Automatically matches the text against the custom lists.
    • Checks for malware and Phishing URL’s.
    • Also supports checks for Personally Identifiable Information (PII).
  • Video moderation API
    • Proactively detects against adult content in the videos.
    • Azure Media Services handles moderation in the Cloud.
  • Human Review Tool beta
    • Review tools lets us review the automated results and approve or change tags to override the automated results.
    • As it uses machine learning and custom lists for moderation, the process gets smarter, while using it.

For pricing, provisioned regions and other key details, read Getting Started with Microsoft Cognitive Services — Content Moderator API.

Knowledge

It maps complex information and data in order to solve intelligent recommendations and semantic search use cases.

Recommendations API

Recommendations API as described by Microsoft is designed to provide personalized product recommendations for your customers and improve the sales in your store.

For pricing, provisioned region and other key details, read Getting Started with Microsoft Azure Cognitive Services – Recommendations API

Academic Knowledge API

The Academic Knowledge API, as described by Microsoft, explores the relationships among the academic papers, journals and authors. Also, it taps into the wealth of an academic content in Microsoft Academic Graph, using Academic Knowledge API.

Interpret

Interpret is a natural language user query string. Get annotated interpretations to enable rich search-box auto-completion experiences that anticipate what you are typing.

Evaluate

Evaluate a query expression and get Academic Knowledge entity results.

Calchistogram

Calculate a histogram of the distribution of the attribute values for the academic entities returned by a query expression, such as the distribution of citations by year for a given author.

For pricing, provisioned regions and other key details, read Getting Started with Microsoft Azure Cognitive Services — Academic Knowledge API.

Summary

Now, you’ve seen how easy is to get started with Cognitive Services. I would highly encourage you to get started with these super intelligent APIs and come up with an intelligent Application.

I hope, you enjoyed this tutorial. If you have any questions or any interesting use cases or suggestions, please comment below. Knowledge grows by sharing! Don’t forget to share this article. If it has helped you, it will also help others.

Thank you. Happy Azure coding.

SHARE ON