This post has been republished via RSS; it originally appeared at: New blog articles in Microsoft Community Hub.
The Microsoft Learn AI Cloud Skills Challenge wrapped up an incredible learning journey with the AI pitch Challenge; a showcase of innovation where passionate learners brought their visions to life through the power of AI. These creators shared how they would harness Microsoft's AI technology to craft solutions for the future in a 3-minute video pitch. Out of many, five outstanding winners emerged, each with a unique and compelling vision.
This series of blog posts spotlights each creator sharing the transformative potential of their ideas.
I’m Hakimi Abdul Jabar also known as A.J. Hakimi and I am the Managing Consultant, Chief Software Developer and Technology Architect and Global InHouse Legal Adviser of The Software Suite™ - a registered international business and global consultancy based in Kuala Lumpur, Malaysia with business addresses in New York, London etc. I am the brain behind the revolutionary tool that is set to change the way the Global Community of Persons with Disabilities such as the visually impaired, physically impaired (e.g. persons without arms, fingers, hands etc.) and others who can only rely on their SPEECH or VOICE, are able to work, earn a living, get jobs etc. in the Global Freelance Economy and even in the Grander Scale of the Global Economy by using an assistive technology (AT) tool that can help anyone who struggle with writing. You may hear it referred to as “speech-to-text,” “voice-to-text,” “voice recognition,” or “speech recognition” technology. It allows users to write with their voices, collate their writings, do AI powered online research on their writing extensively, instead of doing by what is seemingly impossible for the differently-abled, that is writing by hand or with a keyboard – WriteSight! This AI-powered knowledge base and tool is the amalgamation of advanced technology and a profound love for our global community of persons with disabilities, ensuring that every human being with disabilities can be well-informed and proactive in managing their writing as a means of gaining employment, earning a living through writing, freelancing, etc.. All of this can be achieved just by using a good microphone (required), speakers (optional) or headphones (optional) and very good internet connection (required).
Creating a cloud service for the visually impaired and physically disabled using Microsoft Azure AI Cognitive Services involves several components. Here’s a high-level overview of how such a system could be designed:
Speech-to-Text Service: Azure provides a Speech Service that can convert spoken language into written text . This can be used to transcribe the user’s speech into text in real-time.
Text Editor: The transcribed text can be input into an online text editor. This editor could be a simple one for writing articles or a more complex one with features for writing novels and books.
Immersive Reader: Azure’s Immersive Reader is a service that can help users of any age and reading ability with features like reading aloud, translating languages, and focusing attention through highlighting and other design elements. This can be used to read the written text back to the user, helping them review their work.
Accessibility Features: Additional accessibility features can be built into the application to make it more user-friendly for people with all sorts of disabilities. For example, keyboard shortcuts for all actions, high contrast themes for low vision users, etc.
Cloud Storage: Azure provides several options for storing data in the cloud. The user’s work can be saved in an Azure Storage Account for persistence and retrieval.
Web App: All these components can be integrated into a web application hosted on Azure. The web app would serve as the interface for the user to interact with the system.
Text Analytics: It is an information extraction and text analytics service that includes a number of Natural language processing (NLP) capabilities such as sentiment classification, collaborative filtering, key phrase extraction, language identification, and named entity identification. With sentiment analysis, you may obtain a better knowledge of consumer opinions. Natural language processing (NLP) is a branch of artificial intelligence (AI) that enables computers to comprehend, generate, and manipulate human language.
Translator: Translator is an automatic translation service that you may use with a single REST API request to transform text. The service employs cutting-edge machine translation technologies as well as statistical machine translation.
Content creation: AI tools such as Microsoft Bing and GPT-4 is utilized for creative ideation, writing design techniques, and content writing.
Azure Bot Services: The Microsoft Azure Bot Framework and Bot Service to provide users - individuals and employees within organizations an improved self-service experience. Leveraging the Microsoft Azure Bot helps users, employees, employers and organizations eliminate unnecessary delays that often result from human interactions by automating basic inquiries. The Azure Bot Framework and Bot Service not only pull data from disparate locations but aggregate that data to provide an improved experience during common interactions and the bot integration enables end users to conduct these interactions. It unlocks existing infrastructure and investments and provides efficient support and digital transformation.
WriteSight is designed with user-friendliness in mind. Anyone can simply input their verified facts online search via Speech-To-Text, and the AI delves into its extensive knowledge base to provide possible and viable references, suggestions for further comprehension, and advice on when to seek indepth assistance.
The story behind WriteSight is as heartwarming as it is creative and innovative. It all started with my own visibly-impaired masseur, Dutch (name changed for privacy reasons), who had suffered a loss of eyesight due to a vehicular accident. Shidee was avid romance novel writer who made quite good income prior to his tragedy. He needed special equipment that can turn his speech into text as his condition made it a huge struggle for him to write. We had an hour’s long discussion on Enhanced Augmented Artificially Enabled Reality. Twenty (20) years later in 2023, that's when the light-bulb switched on - why not use my legal, corporate finance and digital software and tech background to build a solution and service.
The engine at the heart of WriteSight is a refined version of GPT-4 in Azure OpenAI Service, fine-tuned to understand and process queries specifically as given in the Text-To-Speech format which allows the AI Language Learning Model (LLM) such as ChatGPT powered Microsoft Bing to provide concise, accurate, and relevant information to worried users at any time of the day.
As an Azure user, the Azure OpenAI Service has powerful AI capabilities that allow me to leverage my experience in the cloud as the Azure OpenAI Service can be used to create chatbots, generate text, translate languages, and write different kinds of creative content. As the platform continues to evolve, developers such as myself will be able to use it to build even more powerful and sophisticated applications and apply it to WriteSight. I’m looking forward to building this product with Azure!
Feeling inspired? The Microsoft Learn AI Skills Challenge may have ended but the learning never stops! Get started with an AI Learning Path and find a new Microsoft Learn Cloud Skills Challenge to join. Transform your innovative ideas into reality with Azure credits through the Founders Hub. And for the students who dream of making an impact, the Imagine Cup is currently underway!