The ability to speak and communicate is at the very core of human relationships. Without these, we couldn’t share our thoughts or emotions. So it isn’t surprising that technology is finding a special place in enhancing this very human dimension of our lives. Below are just four of the most recent developments that promise to change the face of speech therapy forever.
Computers: Helping stroke patients with speech impairments
For elderly stroke victims, speech damage is common, debilitating and potentially life transforming. More often than not long periods of therapy are required. Recently an innovative computerized treatment has evolved based on a new and controversial understanding of the way speech works.
Traditional theories posit that speech output is put together sound by sound. However, an alternative model has emerged, arguing that speech is derived from plans stored in the brains containing words and even entire phrases.
Based on this theory, new technology has been developed giving stroke and brain damage patients high-intensity stimulation through images, words, and sounds to try to kick-start damaged nerve systems and get them speaking again. Once the patient matches what he hears with an image on the screen, eventually this “matching” can be extended into talking as well.
Kaspar: helping kids plagued with autism to communicate
Meet Kaspar (not the friendly ghost): you can talk to him, tickle him stroke him, play with him and even prod without being concerned that he will abandon you. Kaspar looks just like a kid with an adorable face, moving features and limbs, yet Kaspar is a robot. He assists kids with autism develop critical social skills through games and activities such as peekaboo.
Kaspar’s primary appeal is that his interactions are simplified and extremely predictable- essential for autistic children who are often overwhelmed by the complexity of normative human communication. Kaspar is non-judgemental and straightforward and has all the time in the world for the child to react- putting his “friends” at ease as they interact and communicate.
Speech recognition: A Gap between human and machine?
Humans have the uncanny ability to filter out a singular voice from the noise of a large crowd and engage others despite their emotional speech or unfamiliar accents. Over the years speech recognition technologies have emerged (converting audio to text), but as whole machines have lagged far behind their human counterparts.
Researchers in the UK have made great strides in shrinking this performance gap and have developed speech technologies that are beginning to mimic human voice recognition. Machines can break down speech into sounds and calculate the probabilities of likely words and sentences utilizing data from individual speakers to learn to recognize their speech.
Teletherapy: Facilitating speech therapy for the masses
Teletherapy is the delivery of speech services online via two-way video conferencing. Teletherapy services are quite similar to traditional speech therapy sessions save for one major exception. Instead of sitting together in the same room, the clinician and the child communicate via live video conferencing.
The cutting-edge technology combined with the plethora of benefits afforded by ever-expanding cyberspace positions teletherapy to be at the precipice of speech therapy of the future. Convenience, cost savings and the ability to provide quality services for previously underserved populations such as those in rural areas bodes well teletherapy for years to come.