Welcome to another edition of Tools of the Trade: Assistive Technology! Assistive technology enables and promotes inclusion and participation, especially of people with disabilities, aging populations, and people with non-communicable diseases.
“The primary purpose of assistive products is to maintain or improve an individual’s functioning and independence, thereby promoting their well-being. WHO estimates that today 2.5 billion people need one or more assistive products such as wheelchairs, hearing aids, or apps that support communication and cognition. With a global ageing population and a rise in noncommunicable diseases, this number will rise beyond 3.5 billion by 2050, with many older people needing two or more products as they age.” (WHO)
In the last edition of Inside Equal Access, we looked at Screen Magnifiers and how they enhanced the digital experience for users with low vision or special sight conditions.
This month, we’ll be looking at Voice Recognition Software, and how it creates a more efficient and accessible digital experience for users with limited motor functions or cognitive bandwidth.
What is voice recognition software?
Voice recognition software, also known as speech recognition or speech-to-text, is a technology that converts spoken words into navigation commands, user input, or written text. Utilizing advanced algorithms and machine learning, voice recognition systems analyze audio input, identify spoken words, and transform them into user commands and transcriptions with remarkable accuracy. This technology has evolved significantly over the years with sophisticated algorithms capable of understanding various accents, dialects, and speech patterns.
This assistive technology is widely used in popular artificial intelligence models such as Google Assistant, Apple's Siri, and Amazon's Alexa. However, it is especially beneficial for users with many different types of disabilities or limitations:
- It can generate captions of live conversations for users who are Deaf or Hard of Hearing
- It can be used to input computer commands and recite information for users who are blind or have low vision
- It can be used to navigate and interact with software for users who have mobility or dexterity-related disabilities, such as the limited use of hands or fingers
- It can help transfer thoughts to written text for users with limited cognitive bandwidth, or who otherwise convey their ideas better by speaking rather than writing
And while this article explores only a couple of these uses, the applications for this assistive technology seem nearly limitless.
How is voice recognition software used?
Much like screen magnifiers, voice recognition software is embedded in most modern operating systems, browsers, and document editing applications. It can be easily activated with just a few selections or changes to settings.
Using voice recognition software on an operating system
| Operating System | Location |
|---|---|
| Windows | System Settings > Accessibility > Speech |
| MacOS | System Settings > Accessibility > Voice Control |
Using voice recognition software in document editing applications
| Application | Location |
|---|---|
| Microsoft Word | Home > Dictate |
| Google Docs | Tools > Voice Typing |
Using voice recognition software on mobile devices
| Device | Location | Activation Command |
|---|---|---|
| Android | Settings > Accessibility > Voice Access | "Hey Google...", "Okay Google..." |
| iPhone | Settings > Accessibility > Voice Control | "Hey Siri..." |
Once activated, voice recognition and dictation features enable the user to navigate applications, input commands, and dictate text while remaining hands-off of the device.
Other features of voice recognition software
Most voice recognition software is customizable and adaptable to users' preferences and needs. Modifying certain settings and enabling certain features can create a more pleasant hands-off experience as well as improve the accuracy of voice commands and dictation.
Some of these features include:
- Languages: Setting the primary language can make it easier for the software to better understand certain accents and dialects.
- Custom (Smart) Commands: Creating shortcuts for customizable commands can make completing complex tasks or inputs easier and benefit users with limited cognitive bandwidth.
- Confirmations: Displaying a visual confirmation or playing a sound to confirm a voice-enabled command has been recognized can be beneficial for users with hearing or sight-related disabilities.
- Grid Controls: Enabling grid overlays allows the software to interact with parts of the screen that don't have interactive controls, or controls that feature complex interactions.
How can we make the digital experience better for voice recognition software users?
Designing and developing content with voice recognition software users in mind means creating a digital experience where users can navigate and execute commands seamlessly using only their voice. Some ways to make your content voice recognition software-ready include:
- Creating interactive elements and inputs that can be easily identified and read
- Avoiding generic link text such as "Click Here" or "Read More," especially when multiple links or buttons use the same text
- Using headings and labels to clearly identify specific sections or regions on a page or application
- Ensuring that form and input labels are correctly associated with the input field that they describe
- Limiting the use of complex interactions (e.g., precision inputs, multi-key inputs, drag-and-drop, etc.)
- Handling errors gracefully and helping users recover with alternatives and suggestions to fix any issues
Explore some of our helpful web resources below to learn about more ways to make the digital experience for voice recognition software users as inclusive and welcoming as possible.
Resources for creating a great digital experience for voice recognition software users
- You're designing a product with voice recognition technology. How can you ensure it's user-friendly? (LinkedIn)
- Voice Interaction Design: The Ultimate Guide (Toaha Nahid)
- Accessible Digital Marketing (Kent State Digital Accessibility Guide)
- Writing Accessible Code (Kent State Digital Accessibility Guide)
- Speech Recognition Perspective and Video (1:11) (Web Accessibility Initiative)
- Optimal Speech Recognition: Putting Your Words into Action (Darren Gabbert, Educause Review)
We hope that you’ve found this article on voice recognition software informative and interesting, and we can’t wait to share more about assistive technology with you in the next edition of Inside Equal Access!