In the early days of voice recognition, you were lucky to have learned half of your words, even if you spoke slowly like a robot. Every smartphone these days has some sort of voice assistant that can quickly take notes for you or perform tasks such as opening apps.
However, if you have a Windows 10 computer, you can also control Windows 10 using your voice. It’s more than just a cool feature. It can actually increase productivity and is an effective way for people with disabilities to take control of their computer.
Control vs. dictation
Do you want to control Windows 10 with your voice, or just want it to record what you say? Voice control is a function other than dictation, and some users often confuse the two concepts. If all you have to do is just talk, and the computer records what you say, you don’t have to go out of your way to set up speech recognition.
For example, Google Docs has a great voice dictation feature that uses the power of the cloud to convert your speech to text. If you’re a macOS user, you can even use Apple’s built-in system
This article is about voice control, not voice dictation In other words, we want to use Windows and perform common tasks without using a keyboard or mouse.
Choose the Right Microphone
If you want to control Windows 10 with your voice, you need to let your computer hear you. If you’re using a laptop or desktop webcam, you already have a basic microphone on hand, but it doesn’t always work well for voice recognition.
Since you already own these microphones, it doesn’t hurt to try voice control with them, but a top-of-the-line microphone will undoubtedly make things better. Here we are using a Samson Go microphone
Tell Windows which microphone to use
Before you can give orders to your computer, you need to specify which microphone it should use. Since Windows supports multiple microphones at the same time, it can sometimes select the default one that is not optimal for voice control.
With a microphone plugged in (assuming it’s an external microphone), it’s fairly easy to select it as an active recording device. Just right click on the speaker icon in the taskbar.
Then click “Open Sound Settings”.
In the pop-up window, under Input, select the microphone that the system should use from the drop-down list.
Setting up speech recognition
To start the activation process for Speech Recognition on your Windows 10 PC, open the Start Menu and type Speech Recognition. Then open it.
In the new window that appears, click “Start Speech Recognition”. You may receive a pop-up warning that Speech Recognition is optimized for native English speakers in the United States. Just click “OK” to close this window.
You will then see this wizard that walks you through the setup process.
Then you need to choose which type of microphone you are using. We’re using a Samson Go microphone that mounts to the desktop (or attaches to the screen), so we’ll go with the desktop microphone.
On the next screen, you will learn how to set up your microphone. It is different for each type of microphone, so we will not show it here.
Now read the sample text to help Windows calibrate your microphone.
If the computer understands you well enough, you can click Next.
You will now see the option to let Windows read your documents in order to understand your vocabulary and phrases. It’s up to you if you want to do this. If you have documents with irrelevant content or have privacy concerns, turn this off.
Ok, we’re almost done. Now all you have to do is select the activation mode.
Basically, you need to decide if you want speech recognition to be turned on by saying a keyword, which means it is always listening, or by using a keyboard shortcut.
You now have the option to print a reference card with general commands.
In all fairness, most people won’t need this as you can always find commands when you need to, but if you’re preparing a computer for a disabled person or less tech-savvy user, it’s handy to print and hang the computer nearby for reference.
Finally, after choosing whether to run speech recognition on startup, you are presented with the option to complete the tutorial. If not, it’s worth it! For those who have gone through the guide, just skip it.
You will see this on the screen when speech recognition is running.
Activate speech recognition using your chosen activation method, although Windows Key + Ctrl will still work as a toggle switch. As a test, simply say the Start Menu with the listening light on. The Start Menu should appear immediately. For more commands, see the official reference card.
What now?
With the basic setup complete, you’re almost ready to control your computer with just your voice. However, you may want to train Windows more so that voice recognition is more accurate. You will find the tutorial app in the Speech Recognition settings you first used to set up your voice recognition.
The more voice samples there are in Windows, the better the system will work. That being said, if you get a lot of missing or misheard commands, take a few minutes to train your voice recognition system.
Cortana and third-party options
It’s nice that Windows 10 comes with a built-in speech recognition app to control Windows 10 with your voice, but is there a better alternative? The truth is, desktop speech control is a pretty niche area. It is often referred to as an accessibility feature. Therefore, there are not so many third-party options.
Interestingly, Windows 10 has a completely separate voice activation system in the form of Cortana As a voice assistant, Cortana is not intended to be a voice replacement for keyboard and mouse, but there are many similarities between the two systems. See what Cortana is capable of, it might be better suited to your specific needs than Universal Speech Recognition.
As far as third-party voice control goes, there isn’t much. The most popular name at the moment is Nuance’s Dragon Speech Recognition. They were the pioneers of computerized speech recognition and are probably the most experienced companies in the field. This is an option worth exploring if you have complex or critical speech recognition needs.
–