The second new direction is using artificial intelligence (AI) to extend the services provided by the speech pathologist so clients can get more practice.
“Science has shown very clearly that a new speech skill needs to be practiced many times – one study suggested as many as 5,000 repetitions – before it becomes the new default for a speaker,” says McAllister. “Clinicians have jam-packed caseloads, which makes it very difficult to achieve those kinds of numbers with any given child, but we’re interested to see if similar results are seen in children who see their clinicians some of the time and complete AI-guided home practice on other days.”
Last year McAllister and her collaborators at Montclair State University and Syracuse University (notably Nina Benway, now a postdoctoral researcher at the University of Maryland) received NIH funding to develop a speech database that can train AI systems to classify children’s “r” sounds as on-target or off-target. The newly funded grant will support the team in integrating this classifier with the staRt app, so children’s home practice can be augmented with biofeedback and AI feedback on accuracy.
Again building off of previous research, McAllister’s second NIH grant, “Improving the Accessibility of Transgender Voice Training with Visual-acoustic Biofeedback,” will provide critical insight into how smartphone- or computer-based software can be used to help transgender people train their voices.
“Some trans people can be negatively impacted if their voice is perceived as incongruous with their gender identity, and they may choose to work with a speech pathologist to achieve a vocal presentation that is comfortable for them,” says McAllister. “In addition to the pitch of the voice, male and female vocal tracts also differ in their resonating characteristics, but resonance is harder to understand than pitch, and harder to target in therapy. The staRt software allows learners to visualize the resonant frequencies of the vocal tract, which could make it easier to adjust them to match a target that is appropriate for their personal speech goals.”
McAllister’s work is a collaboration with Vesna Novak, a transgender computer scientist at the University of Cincinnati. Their project will create and test the first software for gender-affirming voice training that combines real-time information about vocal pitch and resonance with structured exercises.
Researchers in NYU Steinhardt’s Department of Communicative Sciences and Disorders are tackling high-impact treatment research in a variety of ways, using both innovation and technology to improve quality of life.
A new speech therapy app helps kids facing persistent pronunciation challenges get "unstuck."
What do mashed potatoes, black bean soup, and coconut flan have in common? Not only are they foods easy for individuals with dysphagia, a swallowing disorder, to consume, but they are also dishes recently prepared by master’s students from the NYU Steinhardt Department of Communicative Sciences and Disorders and Department of Nutrition and Food Studies taking “Interdisciplinary Case-Based Management in Dysphagia.”