Smart speaker devices can improve speech intelligibility in adults with intellectual disability

Abstract

Background: Successful communication is vital to quality of life. One group commonly facing speech and communication difficulties is individuals with intellectual disability (ID). A novel route to encourage clear speech is offered by mainstream smart speakers (e.g., Amazon Alexa and Google Home). Smart speakers offer four factors important for learning: reward immediacy, spaced practice, autonomy/intrinsic motivation and reduced social barriers. Yet the potential of smart speakers to improve speech intelligibility has not been explored before. Aims: To determine whether providing individuals with intellectual disabilities with smart speaker devices improved ratings of speech intelligibility for (1) phrases related to device use and (2) unrelated words via a semirandomized controlled trial. Methods & Procedures: In a semi-randomized controlled trial, an intervention group of adults with ID (N = 21) received smart speakers, while a control group (N = 22) did not. Before and after about 12 weeks, participants were recorded saying smart speaker-related phrases and unrelated words. Naïve participants then rated the intelligibility of the speech recordings.Outcomes & Results: The group that received smart speakers made significantly larger intelligibility gains than the control group. Although the effect size was modest, this difference was found for both smart speaker-related phrases and unrelated words. Conclusions & Implications: While the mechanism of action remains to be determined, the presence of smart speakers in the home had a demonstrable impact on ratings of speech intelligibility, and could provide cost-effective inclusive support for speech and communication improvement, improving the quality of life of vulnerable populations.

Understanding the possibilities and limitations of assistive technology in health and welfare services for people with intellectual disabilities, staff perspectives

“…Bespoke devices are often high cost and can go out of date, whereas mainstream devices, on the other hand, are relatively low cost and are continually updated by the giant companies who develop them [15]. For example, For example, mainstream smart speakers provide costeffective inclusive support for speech and communication improvement among individuals with ID [48]. However, there is a big range of different devices under the umbrella term of AT, and sometimes, we do not have mainstream alternatives.…”

Voice-Activated Virtual Home Assistant Use and Social Isolation and Loneliness Among Older Adults: Mini Review

“…For example, one study noted racial disparities in the automated speech recognition of VHAs (36). Alternatively, another study involving adults with intellectual disabilities had improvements in speech intelligibility after VHA interactions (37). Additionally, commercially available VHA devices are relatively affordable, but that benefit involves the risk of corporate-infused biases and targeted, personalized marketing opportunities (32), which may pose vulnerabilities for older adults.…”

Conversational Agents in Therapeutic Interventions for Neurodevelopmental Disorders: A Survey

“…Results showed that the participants were able to disclose more during the session with the robot than with the human concealer. Again, Smith et al [74] employed Alexa and Google Home with 21 individuals with intellectual disabilities and let them free to interact with the technology for about 12 weeks to assess intelligibility gains. Meanwhile, a control group of 22 people did not use any conversational technology.…”

“…Improving automatic speech recognition modules would enable more self-ruling conversational agents, which would reduce the human task load. For this reason, future work should pursue improving certain technical drawbacks, especially regarding speech recognition problems, also considering more severe cases of speech impairments [3,27,74,77,81]. As a possible research direction, Smith et al [74] suggested implementing a voice profile option, which allows the speech recognition model to adapt to individual voices.…”