Speech recognition apps can improve literacy, MU study finds

First-grade students who used speech recognition tools averaged a 97.4 percent accuracy rate on post-study reading tests

January 25th, 2018

More than 71 million children and adults in the United States, or 22 percent of the population, are functionally illiterate. However, past research shows that when schools support children who struggle to read early in life, they are more likely to become sufficiently literate and perform better in school. In a recent study, Elizabeth Baker, professor of literacy studies at the University of Missouri, found that speech recognition apps used in early elementary classrooms can help give children who struggle to read an early boost in literacy.

“If speech recognition is available on mobile devices, then the mobile device becomes the proverbial pen,” Baker said. “This means that the student controls what they learn to read; that can be very empowering.”

In the past, an intervention strategy called the Language Experience Approach, where teachers transcribe students’ words for them, was used to help students learn to read. Baker says that while the Language Experience Approach was effective with individual students, it was a time-consuming strategy for teachers and gradually fell out of popularity. Speech recognition technologies, on the other hand, can be used on mobile devices in classrooms to provide a similar individualized experience to students without overwhelming a teacher.

Baker observed a classroom of first-grade students who were learning to read by using speech recognition apps on mobile devices. Baker found that students who used speech recognition apps to learn to read were more eager to try new words and phrases, possibly because the apps allowed them to make mistakes and grow as readers without any embarrassment. A more significant end result, Baker found that the students averaged a 97.4 percent accuracy rate on their post-study reading tests.

“Speech recognition technologies are supportive of the learner because it allows them to use personally, culturally relevant grammar,” Baker said. “Children all have different backgrounds, and this technology allows them to learn to read while using their own frame of reference.”

Baker says the results provide encouraging evidence that speech recognition technologies may not only be beneficial for young students, but also could be adapted to help elementary, middle and high school students, as well as adults who struggle to read. However, Baker warns that many apps on the market do not yet have the safety features necessary to protect young children and be appropriate for school use.

“There’s the possibility that a student says a phrase and an inappropriate word will pop up,” Baker said. “One teacher may not be able to monitor the screens for all the students; an app that has a child safety button would make this learning method more practical.”

“Apps, iPads, and Literacy: Examining the Feasibility of Speech Recognition in a First-Grade Classroom” was published in Reading Research Quarterly. Baker is currently reaching out to potential investors about her idea for a speech recognition-based app that has all the necessary features to help keep kids safe while they learn to read.