Systematic review of 20 computer-based speech support programs - usefulness supported but none used immersive VR
How this was rated
Systematic review across speech-difference populations. Reliability depends on the rigor of included studies; see the review's own quality assessment.
Ratings use a simplified four-tier scheme (High, Moderate, Low, Very Low) informed by the GRADE working group. Learn more about how studies are rated.
This systematic review cataloged 20 computer-based speech support programs targeting articulation and phonological differences. All studies supported their general usefulness, though direct comparisons with human-delivered support produced mixed results. None used immersive VR.
A systematic review suggesting that VR for communication differences is under-researched relative to claims made about it; conclusions reflect a heterogeneous primary literature.
Key findings
- All 20 reviewed studies supported general usefulness of computer-based tools for improving speech outcomes (studies published 2004-2014, English-language only)
- Direct comparisons with in-person support produced mixed results - the review explicitly concludes it cannot be claimed that a consensus exists in the superiority of virtual speech therapists over speech-language pathologists
- None of the reviewed systems used immersive VR - all ran on standard computers
- Hearing-related speech differences were the most frequently targeted area
- A structural tension was identified: publications with rigorous study designs did not describe the technical elements used in their virtual speech therapist; publications that did describe technical elements had poor study designs
Background
As computing power has grown, researchers have explored whether software-based tools can supplement or partially replace in-person speech support. These systems range from simple drill-based programs to animated virtual characters that model speech sounds. By 2016, enough studies had accumulated to warrant a systematic review of what had been tried and how well it worked.
What the researchers did
Chen and colleagues searched multiple databases and identified 20 studies describing computer-based speech support tools. They cataloged each system’s target population, the type of speech difference addressed, the technology platform used, and the outcomes measured. They assessed study quality and compared results across different designs.
What they found
Every reviewed study reported at least some positive outcomes, suggesting that computer-based tools can meaningfully support speech development. However, when these tools were directly compared to in-person support from a speech-language professional, results were mixed - some studies found comparable outcomes, while others found human-delivered support to be more effective. The most commonly addressed area was speech differences associated with hearing loss, followed by articulation and phonological differences in children. Notably, none of the reviewed systems used immersive VR; all ran on desktop or laptop computers with standard screens.
Why this matters
This review established that technology-based speech support was already showing promise over a decade ago, even with relatively basic platforms. The absence of immersive VR from the evidence base at that time highlights how much the field has evolved since. The mixed findings on direct comparisons with human-delivered support suggest that these tools work best as supplements rather than replacements, extending access to practice opportunities between sessions or in areas where specialist services are scarce.
Limitations
The reviewed studies varied widely in quality, sample size, and outcome measures, making direct comparisons difficult. Most studies had small samples and short follow-up periods. The search was limited to English-language publications from 2004-2014, so earlier work and non-English literature were excluded. The review predates the widespread availability of consumer VR headsets, so its findings do not speak to the potential of immersive environments.
A structural limitation identified in the review itself is worth noting: the most rigorous studies did not describe the technical elements of their virtual speech therapists in sufficient detail to enable replication or comparison - while the papers that did describe technical details in depth tended to have weak study designs. This technical-rigour trade-off remains a challenge in the field today.
Implications for practice
Computer-delivered speech support is a promising supplement to in-person services and could extend clinician reach in under-resourced or remote settings.
Where this connects to Therapy withVR
The study above is independent research and does not endorse any product. The notes below are commentary from withVR on how the themes in this research relate to features of Therapy withVR. The research findings are not claims about Therapy withVR.
AI-Generated Conversation
This review examined virtual speech support systems - Therapy withVR's AI features generate contextually appropriate avatar responses, creating the responsive interaction this research identified as important.
Avatar Speech System
Google Text-to-Speech with CHIRP3-HD voice quality and 59+ languages delivers the natural, intelligible avatar communication this review highlighted as essential.
Cite this study
If you reference this study in your work, the canonical citation formats are:
@article{chenypp2016,
author = {Chen Y-PP and Johnson, C. and Lalbakhsh, P. and Caelli, T. and Deng, G. and Tay, D. and Erickson, S. and Broadbridge, P. and El Refaie, A. and Doube, W. and Morris, M. E.},
title = {Systematic review of virtual speech therapists for speech disorders},
journal = {Computer Speech and Language},
year = {2016},
doi = {10.1016/j.csl.2015.08.005},
url = {https://withvr.app/evidence/studies/chen-2016}
}TY - JOUR
AU - Chen Y-PP
AU - Johnson, C.
AU - Lalbakhsh, P.
AU - Caelli, T.
AU - Deng, G.
AU - Tay, D.
AU - Erickson, S.
AU - Broadbridge, P.
AU - El Refaie, A.
AU - Doube, W.
AU - Morris, M. E.
TI - Systematic review of virtual speech therapists for speech disorders
JO - Computer Speech and Language
PY - 2016
DO - 10.1016/j.csl.2015.08.005
UR - https://withvr.app/evidence/studies/chen-2016
ER - Know of research that should be in this hub? If a relevant peer-reviewed study is not listed here, send the reference to hello@withvr.app. The hub is kept up to date as the literature grows.
Funding & independence
No withVR BV involvement in funding, study design, or authorship. Summary prepared independently by withVR using the published paper.