Comment: Nobody has blogged on this paper so I can't really comment...
(All from the University of Illinois)
In this particular study, Hailpern et al. presented the Spoken Impact Project (SIP) which was designed to be used by children (with the help of a professional) with Autism Spectrum Disorder (ASD) in order to increase the rate of vocalizations produced by the children. Children with low-functioning ASD have trouble communicating and may never even develop speech or language skills. ASD children also tend to withdraw into their own world and do not like human interaction which makes acquisition of language skills extremely difficult.
With this in mind, SIP included a computer system that reacted to sounds produced by a child by giving audio, visual, or combined audio and visual output that is meant to stimulate the child to producing more sound. The team was focused on getting the child to produce what they called SSLV, or, Spontaneous Speech-Like Vocalizations, which is a parameter based on classical autism treatments.
After running a base test without feedback on 5 different children, the children used the system in several different sessions where each session had a different kind of feedback.
After the data from the test were gathered and statistical analyses were run, it was found that 3 children reacted to/preferred audio feedback and 2 reacted to visual feedback. It was also found that providing feedback encouraged a positive response from the children. 1 particular child's responses were particularly strong so a follow up study was run on what was called a "Wizard-of-Oz" system which was based on SIP. The child was given the prompt, "Say [word]" and was rewarded with both visual and audio feedback. At the end of the session, the child would repeat all the words that were given to him.
It is encouraging to see research being taken on for helping these kinds of kids and actually producing some positive results. Future researchers and current therapists for this problem should focus on integrating a fun and flexible system that can adapt to a child's preference of either visual or audio feedback and getting that system to teach them actual language skills and communication.
I think SIP is on the right track. The only drawback is that it needs to keep going.
Also it would be nice to see a study taken on with a larger population. Statistically speaking, they needed a larger population and more trials to get more significant results.