Discovering the power of Applied AI Services using Microsoft Azure

Applied AI Services

Applied AI Services is a well-defined suite of cloud-based artificial intelligence (AI) and machine learning (ML) tools and services offered by Microsoft Azure. Azure Cognitive Services is one of the applied AI services that enables developers to easily build and deploy applications without requiring expertise in AI or ML.

Categories of Applied AI Services

Azure Applied AI Services provide a range of services, including,

• Vision Studio
• Language Studio
• Speech Studio
• Azure Open AI Studio
• Form Recognizer Studio

Vision Studio

This service can be used for the ability to read text, analyze images, and detect faces with technology like optical character recognition (OCR) and machine learning.

The following are the capabilities of vision studio, namely,

• Video summary and frame locator- Generate a summary of the main points in the video and locate specific keywords and jump to the relevant section, and it's still in the preview mode.
• Extract text from images- Extract printed and handwritten style text from images and documents for supported languages.
• Search photos with natural language- Retrieve specific moments within your photo album. For example, you can search for a birthday party you attended last month, your favorite places, or your pet or birds, and it's still in preview mode.
• Add captions to images- Generate a human-readable sentence that describes the image's content, and still, it's in preview mode.
• Dense captioning- Generate human-readable captions for all important objects detected in your image, and still, it's in preview mode.
• Detect common objects in images- Recognize the location of objects of interest in an image and assign them a label.
• Extract common tags from images- Use an AI model to automatically assign one or more labels to an image, and still, it's in the preview mode.
• Detect sensitive content in images- Detect sensitive content in images so you can moderate their usage in your applications.

Language Studio

This service includes natural language processing (NLP), sentiment analysis, language detection, and text translation. The following are the capabilities of language studio, namely,

• Extract named entities- Identity different entities in the text and categorize them into pre-defined types.
• Extract health information- Extract and label relevant health information from unstructured text.
• Custom-named entity recognition- Train an extraction model to identify your domain categories using your data.
• Extract PII- Identify sensitive entities in the text associated with an individual.
• Extract key phrases- Identify the most important points in a piece of text.
• Analyze sentiment and mine opinions- Detect positive, negative, and neutral sentiments in text. Get more insights by mining options.
• Detect Language- Evaluate text and detect various languages and variant dialects.
• Custom text classification- Train a classification model to classify text using your data.

Speech Studio

These services enable developers to integrate speech recognition and synthesis capabilities into their applications, supporting multiple languages and dialects. Azure Speech Services features like Speech-to-text and Text-to-speech. The following are the capabilities of language studio, namely,

Speech to Text

• Quickly and accurately transcribe in more than 100 languages and dialects. Enhance the accuracy of your transcriptions by creating a custom speech model that can handle domain-specific terminology, background noise, and accents.
• Real-time Speech to text- Quickly test live transcription capabilities on your own audio without writing any code.
• Custom speech- Add your data and adapt to specific speaking styles, vocabulary, and more with a customized speech-to-text model.
• Pronunciation Assessment- Get instant feedback on pronunciation accuracy and fluency by reading a script aloud.

Text to Speech

• Build apps and services that speak naturally with more than 400 voices across 140 languages and dialects. Create a customized voice to differentiate your brand and use various speaking styles to bring a sense of emotion to your spoken content.
• Voice Gallery – Browse expressive voices with humanlike speech to find the perfect speaker for your project.
• Custom Voice – Use your audio recordings to create a distinct, one-of-a-kind voice for your text-to-speech apps.
• Audio Content Creation – Craft nuanced speech by adjusting the speaking style, pacing, and pronunciation of your spoken content.

Form Recognizer Studio

It is one of the Applied AI services and Cognitive Services which uses Optical Character Recognition (OCR) and Machine Learning (ML) technology to identify and extract key/value pairs and table data from form documents using prebuilt models or create your custom models.

The following are the capabilities of the form recognizer studio, namely,

• Invoices- Extract invoice ID, customer details, vendor details, ship to, a bill to, total tax, subtotal, and so on.
• Receipts- Extract time, date of the transaction, merchant information, amount of taxes, totals, and more.
• Business Cards- Extract a person's name, job title, address, email, company, and phone number from business cards.
• Identity Documents- Extract name, expiration date, machine-readable zones, and more from passports and ID cards.
• Health Insurance Cards- Extract insurer, member, prescription, group number, and more information from US health insurance cards.
• US Tax W-2- Extract employee, employer, and wage information from US W-2 Tax Form.
• US Tax 1098- Extract mortgage interest information from US 1098 Tax Form.
• US Tax 1098 -E- Extract student loan information from US 1098 – E Tax Form.
• US Tax 1098 -T- Extract tuition information from US Tax 1098 – T form.
• Contracts- Extract the title and signatory parties' information, including names, reference names, and addresses from contracts.

Azure Open AI Studio

Get example prompts for different scenarios and write prompts of your own. Export your prompts to code at any time to rapidly iterate at scale and integrate with your apps. There are two types of playgrounds available one is the completion playground and the ChatGPT playground, which is in preview mode.

The following are the capabilities of Azure Open AI studio, namely,

• Summarize an article- It is used to summarize an article where you can extract important bullet points from the article with more specific details.
• Generate product name ideas- It is used to generate product key features and evoke positive emotions.
• Natural Language to SQL- It translates the natural language to SQL queries.
• Classify Text- It is used to classify items into categories provided at inference time.

Summary

In this article, we learned about the different types of Applied AI services in Microsoft Azure and its various capabilities and offerings. This service will help our customers to drive the best business outcomes. All these services are brand new. Perhaps Microsoft Azure was grouping them into studios which is the one-stop we can access for the benefit of our customers.