Elsevier

Computer Speech & Language

Volume 37, May 2016, Pages 98-128
Computer Speech & Language

Review
Systematic review of virtual speech therapists for speech disorders

https://doi.org/10.1016/j.csl.2015.08.005Get rights and content

Highlights

  • A systematic review on virtual speech therapists (VSTs) was presented.

  • The comparison of VSTs and traditional speech therapy was discussed.

  • We analyzed intervention methods used in VSTs such as articulation therapy.

  • Hearing impairments was observed as the most frequent disorder targeted by VSTs.

  • We explored 3D virtual heads and games as efficient therapy delivery approaches.

Abstract

In this paper, a systematic review of relevant published studies on computer-based speech therapy systems or virtual speech therapists (VSTs) for people with speech disorders is presented. We structured this work based on the PRISMA framework. The advancements in speech technology and the increased number of successful real-world projects in this area point to a thriving market for VSTs in the near future; however, there is no standard roadmap to pinpoint how these systems should be designed, implemented, customized, and evaluated with respect to the various speech disorders. The focus of this systematic review is on articulation and phonological impairments. This systematic review addresses three research questions: what types of articulation and phonological disorders do VSTs address, how effective are virtual speech therapists, and what technological elements have been utilized in VST projects. The reviewed papers were sourced from comprehensive digital libraries, and were published in English between 2004 and 2014. All the selected studies involve computer-based intervention in the form of a VST regarding articulation or phonological impairments, followed by qualitative and/or quantitative assessments. To generate this review, we encountered several challenges. Studies were heterogeneous in terms of disorders, type and frequency of therapy, sample size, level of functionality, etc. Thus, overall conclusions were difficult to draw. Commonly, publications with rigorous study designs did not describe the technical elements used in their VST, and publications that did describe technical elements had poor study designs. Despite this heterogeneity, the selected studies reported the effectiveness of computers as a more engaging type of intervention with more tools to enrich the intervention programs, particularly when it comes to children; however, it was emphasized that virtual therapists should not drive the intervention but must be used as a medium to deliver the intervention planned by speech-language pathologists. Based on the reviewed papers, VSTs are significantly effective in training people with a variety of speech disorders; however, it cannot be claimed that a consensus exists in the superiority of VSTs over speech-language pathologists regarding rehabilitation outcomes. Our review shows that hearing-impaired cases were the most frequently addressed disorder in the reviewed studies. Automatic speech recognition, speech corpus, and speech synthesizers were the most popular technologies used in the VSTs.

Introduction

Humans are social creatures and communication via speech enables humans to interact and share thoughts in a way which is not possible for any other species. Speech impairment has been shown to have an adverse impact on learning, literacy, applying knowledge, developing and maintaining relationships with friends and family, and securing and keeping a job (McCormack et al., 2009). Any disorder in speech will degrade a person's role in society, dissuading them from interacting in social activities in a way that exploits their potential. This may lead to other social anxiety disorders and avoidance behavior (Beilby et al., 2012, Hawley et al., 2013, McLeod et al., 2013). Considering the wide range of speech impairments, the prevalence of people with such disorders, and the related undesirable consequences on society, the importance of appropriate and comprehensive rehabilitation programs is evident (Bhattacharyya, 2014). An inquiry published by the Senate Standing Committees on Community Affairs of Australia in 2014 (Report, 2014), for instance, reported an estimation of more than 1.1 million Australians with a communication disorder which is around 5% of the Australia population. Taking advantage of the advances in both software and hardware in computer systems and also the micro-miniaturization and mobility, computer-based speech therapy (CBST) environments, referred to as virtual speech therapists (VSTs), are becoming increasingly popular (Kagohara et al., 2013). Compared with traditional speech therapy, these environments are gaining increasing acceptance because of their versatility, availability, portability, and controllability (Abad et al., 2013, van Vuuren and Cherney, 2014). They can provide a solution to the shortage of speech-language pathologists (SLPs) in schools or in regional areas by reducing the number of face-to-face therapy sessions, resulting in more affordable services as well. They are also capable of delivering impartial judgements as feedback and provide useful automatic profiling materials (Henshaw and Ferguson, 2013, van Vuuren and Cherney, 2014).

To the best of our knowledge, this is the first systematic review on virtual speech therapists (VSTs). It contains studies that state the intention to test the effects of VST programs on articulation and phonological disorders due to conditions such as dyslalia, aphasia, dysarthria, childhood speech-sound disorder, residual articulation errors (e.g. lisping), or hearing impairment; however, we did not consider other disorders that may affect people's voice and speech such as Alzheimer's disease (Mesulam et al., 2014), autism (Khowaja and Salim, 2013) and Down's syndrome (Laws and Hall, 2014) to exclude individuals with concomitant cognitive impairment that can affect the success rate of articulation and/or phonological therapies and potential ability to engage with VSTs versus face-to-face therapy. To select the related studies, extract the information and present the results, we followed the PRISMA Statement (Liberati et al., 2009) focusing on three research questions: (1) what types of articulation and phonological disorders have VSTs addressed, (2) how effective was the VSTs in the therapy, and (3) what technological elements have been utilized in VST projects.

In the next section, we propose a description for VST and several features that a VST should support. This definition will be our reference for the term VST throughout the paper. Section 3 deals with previous reviews on VST. Section 4 describes our method to prepare this systematic review. We study the extracted results in detail in Section 5. An overall discussion on the results is presented in Section 6, and finally Section 7 concludes the paper.

Section snippets

Virtual speech therapist characteristics

Considering different intervention frameworks, an overall regime for the majority of speech-communication therapy starts with the assessment of the patient's strengths and weaknesses. The SLP designs an appropriate therapy program based on the profile of the person under therapy, the disorder, and short and long-term targets. The outcomes of the therapy sessions are evaluated using specific materials and tables (Chien et al., 2014). To the best of our knowledge, no computer-assisted speech

Previous literature reviews

We carried out a search to find any types of reviews on virtual speech therapy and to the best of our knowledge, this paper is the first systematic review on VSTs. We found several reviews in other related fields which address computer-assisted language learning (Golonka et al., 2012, Henshaw and Ferguson, 2013, Lidström and Hemmingsson, 2014) which may be useful for the reader; however, we do not include them in this paper since the focus is on articulatory and phonological skills in speech

Method

To carry out a standard and transparent systematic review, a process based on the PRISMA Statement was followed (Liberati et al., 2009). Studies were eligible if a computer-based therapy was utilized in a speech therapy for articulation and phonological disorders. They were also required to present quantitative or qualitative assessments and have the potential to cover the three research questions:

  • 1.

    What types of articulation and phonological disorders have VSTs addressed?

  • 2.

    How effective were the

Results

As mentioned in the previous section, a total number of 20 articles on using VSTs in speech-language therapy between 2004 and 2014 were shortlisted. Fig. 2 details the publication trend of the shortlisted papers. In relation to the digital libraries, four of the selected publications were retrieved from the PubMed digital library (Massaro and Light, 2004, Segers and Verhoeven, 2004, Silva et al., 2012, Thompson et al., 2010), followed by three publications from ScienceDirect (Abad et al., 2013,

Discussions

We encountered a great deal of heterogeneity when generating this systematic review. Focusing on our research questions, we attempted to manage the extracted information to draw an organized and structured conclusion. Here we discuss the limitations of this systematic review and present our findings according to our research questions. The quality of some of the studies was generally low, sample sizes were small and procedures were not outlined in sufficient detail. Interventions, outcome

Conclusion

This systematic review was written based on the PRISMA Statement to study papers published on virtual speech therapy environments developed for speech disorders. Data extraction was undertaken based on the following three research questions: What types of articulation and phonological disorders do VSTs address? How effective are virtual speech therapists? and What technological elements have been utilized in VST projects? The studies were very heterogeneous in terms of targeted disorders,

References (54)

  • D. Moore et al.

    Discrimination training of phonemic contrasts enhances phonological processing in mainstream school children

    Brain Lang.

    (2005)
  • J. Rong et al.

    Acoustic feature selection for automatic emotion recognition from speech

    Inf. Process. Manage.

    (2009)
  • O. Saz et al.

    Tools and technologies for computer-aided speech and language therapy

    Speech Commun.

    (2009)
  • J. Bench et al.

    The Bkb (Bamford–Kowal–Bench) sentence lists for partially-hearing children

    Br. J. Audiol.

    (1979)
  • B.L. Berg et al.

    Qualitative Research Methods for the Social Sciences

    (2011)
  • J. Beskow et al.

    Visualization of speech and audio for hearing impaired persons

    Technol. Disabil.

    (2008)
  • N. Bhattacharyya

    The prevalence of voice problems among adults in the United States

    Laryngoscope

    (2014)
  • B.N. Buran et al.

    A sensitive period for the impact of hearing loss on auditory perception

    J. Neurosci.

    (2014)
  • S. Chaisanit et al.

    Interactive multimedia courseware of vowel training for the hearing impaired

  • R. Cole et al.

    A virtual speech therapist for individuals with Parkinson's

    Dis. Educ. Technol.

    (2007)
  • M. Danubianu et al.

    TERAPERS – intelligent solution for personalized therapy of speech disorders

    Int. J. Adv. Life Sci.

    (2009)
  • T. Duarte et al.

    Speech recognition for voice-based machine translation

    Software, IEEE

    (2014)
  • O. Engwall et al.

    Designing the user interface of the computer-based speech training system ARTUR based on early user tests

    Behav. Inform. Technol.

    (2006)
  • E. Eriksson et al.

    Design recommendations for a computer-based speech training system based on end user interviews

  • S. Fagel et al.

    A 3-D virtual head as a tool for speech therapy for children

    Interspeech

    (2008)
  • N. Frederickson et al.

    Phonological Assessment Battery (Manual and Test Materials)

    (1997)
  • J. George et al.

    Developing multimedia interfaces for speech therapy

    Univ. Access Inf. Soc.

    (2010)
  • Cited by (44)

    • Reference architecture design for computer-based speech therapy systems

      2023, Computer Speech and Language
      Citation Excerpt :

      This section describes the background on OSTSs and related works concerning the use of architectures for OSTSs, general RA design and documentation. A wide variety of OSTSs have been proposed to support speech therapy activities (Chen et al., 2016; Darejeh et al., 2019; Furlong et al., 2017). The adoption and use of computers for speech therapy are called computer-based speech therapy (CBST) (Furlong et al., 2017).

    • Towards a speech therapy support system based on phonological processes early detection

      2021, Computer Speech and Language
      Citation Excerpt :

      However, several barriers are found in speech therapy, especially in developing countries: the lack of resources, rehabilitation centers and qualified personnel to provide intervention services, the work overload of professionals, and the poor development or adaptation of assistive technologies according to patients needs (Robles-Bykbaev et al., 2016). In order to face these difficulties, many studies have proposed computer-based speech therapy systems or virtual speech therapists (VSTs) for people with speech disorders (Chen et al., 2016). Also, the related literature presents studies focused on the development of speech recognition systems (Abad et al., 2013; Grossinho et al., 2016; Caballero-Morales and Trujillo-Romero, 2014; Bolaños et al., 2011) for supporting SLPs in clinical environment.

    • The influence of type of feedback during tablet-based delivery of intensive treatment for childhood apraxia of speech

      2020, Journal of Communication Disorders
      Citation Excerpt :

      It is here that computer-based or app-delivered home practice can be useful for strict protocol delivery as well as increasing a child’s engagement and motivation to participate in speech homework (Hair, Monroe, Ahmed, Ballard, & Gutierrez-Osuna, 2018; Nordness & Beukelman, 2010; Toki & Pange, 2010). Computer software packages designed to act as a virtual speech-language pathologist (SLP) can be effective for a range of pediatric speech disorders (Chen et al., 2016; Furlong, Erickson, & Morris, 2017). Fewer than half of the programs in two recent review papers provided feedback to the user on speech attempts (Chen et al., 2016; Furlong et al., 2017).

    View all citing articles on Scopus

    This paper has been recommended for acceptance by K. Kirchhoff.

    View full text