Assistive Voice Technology: the Real-time
Solution to Express Yourself
Supportive communication technologies are crucial in enhancing interaction for individuals with speech impairments. Many forms of these technologies, such as text-to-speech devices, convert typed text into synthetic speech, enabling those who can use manual input or eye-tracking technologies to communicate effectively. Speech-generating devices (SGDs) are tailored with pre-programmed and customizable phrases, facilitating daily communication and social interactions. Voice Output Communication Aids employ digitized pre-recorded human voices and synthesized speech, allowing users to express themselves through touchscreens and buttons.
Using the Source-Filter Model explained earlier, we can categorize assistive speech technology based on the combination of the user's ability to generate enough sound for intelligible speech and their ability to articulate well enough for intelligible speech:
Automatic Speech Recognition (ASR) for non-standard speech is for people who are able to generate enough sound but have bad articulation because of disorders that degrade articulation, such as ALS, MS, stroke, and Parkinson's Disease.
Other Augmentative Alternative Communication (AAC) technologies and tools are for people who can't produce any speech sound and/or have articulation that is too difficult to be recognized by ASR. Think of locked-in syndrome or severe cases and combinations of the earlier-mentioned disorders.
