Voice recognition software, also known as speech to text software, allows an individual to use their voice instead of typing on a keyboard. Voice recognition may be used to dictate text into the computer or to give commands to the computer such as opening application programs, pulling down menus, or saving work.
Voice recognition software may be a an efficient way of documenting thoughts, writing stories or completing assignments. It may be useful for someone who finds keyboards difficult to use and it can assist those who have difficulty with transferring ideas onto paper, because it helps take the focus out of the mechanics of writing (mechanics such as spelling and sentence structure for example). It is important to remember that not all speech recognition software packages are equal in function, capability, or ease of use.
Discrete speech recognition vs Continuous speech recognition
Early voice recognition applications used Discrete speech recognition that required each word to be separated by a brief pause so the software could determine where one word stopped and the next began. Continuous speech recognition applications don’t require a distinct pause to recognize words. Discrete speech recognition software is less readily available because of the ongoing advancements in continuous speech recognition software.
Voice recognition software requirements
All speech recognition software requires a sound card and microphone. The microphone captures the user’s speech and the sound card converts the speech into a digital form that the software can interpret. This digital representation is compared to a profile of the user’s speech. The software creates this profile by having the user initially go through a training exercise in which they are asked to speak specific sentences and words. By comparing spoken words with the user profile, the software determines which words the user probably spoke. The software also uses a general user profile (based on speech from many people) and grammar rules and relationships between words to improve recognition. While the accuracy of voice recognition has improved significantly over the years, some users still experience problems with accuracy.
Digital voice recorders are frequently used with voice recognition software. These allow the user to dictate text into the voice recorder which can be translated at a later date by a voice recognition system.
Voice recognition as a built-in function
Voice recognition software has become a common built-in function in devices, especially tablets and smartphones. Comparing the voice recognition capabilities and ease of use may help determine if built-in will work for an individual or if they might require a different solution. Make sure to test the software for specific functionalities an individual may be using it for—longer blocks of text, for example, may require more robust software solutions than what is offered on a tablet or smartphone.
Want to learn more about speech to text software?
Ottawa Network for Education created videos for students who are interested in learning about or starting to use technologies for reading, writing and other school work. To learn more about speech to text software, visit Ottawa Network for Education’s website to watch a video titled ‘AT Tools for Writing’ and ‘Tools for Writing and Editing.’
Questions to consider when choosing Voice Recognition Software
Features
-
- Can the software be used for both dictation and control of the computer or device?
- What languages and accents does it support?
- How fast is it at translating your voice into words or actions?
- Does it have macro compatibility? (i.e., can you program simple commands that can be used to type long blocks of text or execute more complicated series of operations)? Sometimes macros can be used to control other types of technology (e.g., magnification keyboard shortcuts)
- Does it allow for wireless dictation, i.e., Bluetooth compatible?
- Does it allow you to import/export word lists and user profiles?
- Is portability required? Does it allow for transcription from a digital voice recorder? Consider choosing a model compatible with the voice recognition software.
- Does it need to work with other technology (e.g., screen reading technology for users with low vision) and are there compatible options or bridge programs (i.e. programs that make the two work together)?
Usability
-
- How comfortable is the user typing using their voice? Can they compose their thoughts or commands while the microphone is on?
- What is the learning curve of the software? (i.e. how quickly will it learn your voice, do you need to learn how to “correct” or “train” the program to understand your voice?) How easy is it to program new words or names?
- How forgiving is the software for variations in speech (e.g., unique accents, stuttering, limited breath, etc.)?
- How does it provide feedback that the microphone is on or that the words have been typed correctly? (e.g., visual, auditory)
- Is there an option to have dictated text read aloud?
- Does it have a user-friendly interface (i.e. menu, toolbar, control panel)? How complex is the menu or toolbar structure? How easy is it to adjust settings? How easy is it to program custom commands if available?
Compatibility
-
- Is it compatible with your computer or device’s operating system? Does it integrate with existing applications (e.g., your word processing program, collaborative platforms, internet browsers)?
- Does it ship with its own microphone?
- Can the student position their own microphone?
- Will you need a USB microphone (since it comes with its own sound card)?
- Are there additional features or custom options that match your users’ needs? (e.g., adjusting the visual feedback, choices, or lists by displayed size, font, or adding auditory feedback)
Support
-
- What type of built-in tutorial are available? What are other supports available for users?
- Is there a trial period or demo copy for testing out the software?
- How will you get support if you need it? (e.g., a technician in the school, a local vendor, by telephone, by email, remote access, etc.)
- How much do upgrades cost? Is there any software management agreement or upgrade package that can be purchased?
- What is the payment model? (e.g., purchase, pay per use)
Resources
Manufacturers of Voice Recognition Software
SNOW does not endorse any of the following software/hardware. These links are provided for information purposes only.
Nuance – Dragon Naturally Speaking – Home, Premium, and Individual versions (Windows); Dragon Individual (Mac); also has various medical, legal, and other specialized options
goQSoftware. – SpeakQ (requires WordQ) (Windows)
Software Programs that use Voice Recognition Technology
iCommunicator – older software that uses voice recognition technology to convert spoken language into sign language for those who are deaf and hard of hearing.
Metroplex Voice Computing, Inc. – has developed hands/mouse free software which utilizes voice recognition technology to dictate math.
Trigram Technology – has developed software to be used with voice recognition technology including Language Models that assist those using medical terminology during dictation. This software helps to increase accuracy rates
Free/Open Source Software
Gnome Voice Control (Linux)
Open Mind Speech (Linux)
Perlbox (Linux)
Built-In Voice Recognition
Your computer or device may have free built-in speech recognition software available. Learn more about the accessibility features of your computer or device.
Additional Links
Say I Can – provides tips and instructional videos for using voice recognition software