Technology assisted speech and language therapy

https://doi.org/10.1016/j.ijmedinf.2004.03.005Get rights and content

Abstract

Speech and language therapists (SLTs) are faced daily with a diversity of speech and language disabilities, which are associated with a variety of conditions ranging from client groups with overall cognitive deficits to those with more specific difficulties. It is desirable that those working with such a range of problems and with such a demanding workload, plan care efficiently. Therefore, the introduction of methodologies, reference models of work and tools, which significantly improve the effectiveness of therapy, are particularly welcome. This paper describes the first web-based tool for diagnosis, treatment and e-Learning in the field of language and speech therapy. The system allows SLTs to find the optimum treatment for each patient, it also allows any non-specialist user—SLT, patient or helper (relative etc.)—to explore their creativity, by designing their own communication aid in an interactive manner, with the use of editors such as: configuration and vocabulary. The system has been tested and piloted by potential users in Greece and the UK.

Introduction

Emerging at the beginning of the last decade, the World-Wide Web (WWW) rapidly imposed itself as a new medium for interconnecting people throughout the world. Overstepping the initial publishing purpose, Web applications are currently evolving towards the setting-up of virtual working and communication spaces, intended for use by specific communities of users [1]. Today the use of the WWW for telemedicine applications seems a compulsory solution, and has become a standardized infrastructure for giving access to sophisticated telemedicine applications from virtually any machine and operating system. Such a standardized communication platform guarantees accessibility and usability advantages to both customers (patients) and providers (physicians) [2].

SLTs traditionally work in face-to-face situations with clients (patients) either individually or in groups assessing and treating a wide variety of communication disorders. They see clients on a regular basis but rely on their recommended treatment being followed by relatives, caregivers or untrained helpers at home between therapy sessions. They are faced on a daily basis with a diversity of speech and language disabilities, which are associated with a variety of conditions. Therefore, the introduction of methodologies, reference models of work and tools, which significantly improve the effectiveness of therapy, are particularly welcome.

The introduction of new technologies in speech and language therapy is critical for two main reasons:

  • 1.

    Shortage of SLTs: a significant problem in many geographical areas is the shortage of SLTs as in most countries the profession is quite new. For this reason the population of rural areas faces the problem of limited or no professional assistance that in many cases leads to catastrophic results.

  • 2.

    Carry over problem: one of the problems in any technology-assisted treatment is the carry-over aspect. The problem relates to whether there is any carry-over form of therapy for the patient outside the SLTs immediate working environment and outside of the patient’s home when they leave the house either occasionally (for vacation etc.), or permanently (work purposes etc.).

Given the rapid advances in technology in the later part of the 20th century, one might expect the heavy workloads faced by SLTs to have been at least ameliorated by the development of computer based teaching, treatment and diagnosis team work methods and aids to improve the therapeutic process. However, the use of visual speech aids (VSAs) that are currently employed by SLTs have proven to be problematic for a variety of reasons [3].

Existing VSAs are reported to suffer from:

  • Very low usefulness in speech therapy sessions.

  • Difficulty in handling a variety of caseloads (adults and children).

  • Inability for remote and domiciliary use.

  • Lack of standardization that does not allow their integration.

In addition, they do not address the problem of remote collaboration in cases where SLTs specialising in the treatment of different types of cases, could work as a team with patients and helpers, by associating and integrating different treatment methods.

The main objective of Telelogos is to offer an alternative approach to technology-assisted speech therapy. The Telelogos system enables users to work as a team accessing and using existing VSAs as well as other commercial systems and state of the art technologies. The second objective is related to the increase of the percentage of caseloads targeted as studies [3] have revealed that existing VSAs are being used in less than half of the caseloads, and that the mean caseload for which a VSA is applicable is between 20 and 40%. The Telelogos system has improved the existing situation by making the system applicable to at least 50–60% of the mean caseload and more than 70% of the caseloads targeted.

Section snippets

Conceptual system design

The Telelogos system is based on three main concepts: public awareness, reference and evaluation.

System architecture

Telelogos allows users to work as a team, and to access and use existing VSAs as well as other commercial systems and state of the art technologies. It allows SLTs to find the optimum treatment for each patient, by incorporating different treatment factors. In addition, it also allows any non-specialist user—SLT, patient or helper (relative etc.)—to explore their creativity, by designing their own communication aid in an interactive manner, with the use of editors such as: configuration and

System functionality

In this section, we describe the main functionality of the system by exploring the three conceptual modules (public awareness, reference and evaluation) as they were described in Section 3.

System testing and evaluation

The process of system testing is a necessary and crucial process for any technological tool and provides an important insight for the system in question, which highlights its strengths and weaknesses and allows necessary alterations before actual use by its potential users. After the system release, Telelogos was evaluated to assess its capability to successfully meet user expectations. The feedback of the evaluation method (questionnaire) provided evidence on the effectiveness of the system by

Conclusions

The evaluation results were very promising and demonstrated user satisfaction. The efficacy of the system both in technical and user interface terms is more than satisfactory. Regarding the functionality of the system, users reported that it proved extremely helpful because it contains a multitude of useful information that can be easily accessed thus reducing dramatically the time required for data retrieval.

In conclusion, we can say that Telelogos contributes to the improvement of:

  • (a)

    Health

References (16)

  • R Bellazzi et al.

    Web-based telemedicine systems for home-care: technical issues and experiences

    Comput. Methods Progr. Biomed.

    (2001)
  • C. Vanoirbeek, Y.A. Rekik, N. Karacapilidis, O. Aboukhaled, N. Ebel, J.P. Vader, A web-based information and decision...
  • K.R Coventry et al.

    Specialist speech and language therapists’ use and evaluation of visual speech aids

    Eur. J. Disorders Commun.

    (1997)
  • X Li et al.

    Create, edit, and manage Web database content using active server pages library

    Hi Technol.

    (2002)
  • T Govindasamy

    Successful implementation of e-Learning pedagogical considerations

    Internet Higher Educ.

    (2002)
  • L. Kirpotin, E. Levanti, E. Kardamitsi, M. Kabouroglou, Phonetic and Phonological Development for Children, Research...
  • International Phonetic Association, Handbook of the International Phonetic Association: A Guide to the Use of the...
  • B Roy et al.

    Intérêt d’une épreuve de repérage des troubles du langage lors du bilan médical de l’enfant de 4 ans (ERTL 4)

    Méd. Hyg.

    (1993)
There are more references available in the full text version of this article.

Cited by (22)

  • An overview of the digital solutions for helping people with aphasia through bibliometric analysis

    2021, eNeurologicalSci
    Citation Excerpt :

    The introduction of digital solutions to treatments can not only provide the choice of place whether treatments can be done but also enable the people with aphasia to self-administer their treatments (Marshall et al. [34]). The speech therapists can remotely monitor the progress of people with aphasia through recorded sessions against standardized performance metrics (Glykas and Chytas [25]). A recent study investigated the use of a smart tablet to self-administer the treatments of people with aphasia.

  • Comparison of the computer–aided articulation therapy application with printed material in children with speech sound disorders

    2018, International Journal of Pediatric Otorhinolaryngology
    Citation Excerpt :

    Recently, new CAST applications were developed in many languages. Among a few examples of these applications are APLo [20], OLP (Ortho–Logo–Pedia) Project [21], Vocaliza [22], Speco [23], TERAPERS [24], Telelogos [25]. Gradually, printed materials are replaced by CAST since they are incapable of handling the case–loads, inability for remote and domiciliary use and lack of standardization [26].

  • A speech pronunciation practice system for speech-impaired children: A study to measure its success

    2016, Research in Developmental Disabilities
    Citation Excerpt :

    Although the ASR systems were originally intended for individuals without any speech impairments, several ASR-based applications have been developed for speech-impaired individuals. One of them is the speech pronunciation practice (SPP) system for children with speech impairments, which enables children to practise and improve their speech pronunciation on their own (Glykas and Chytas, 2004; Vaquero, Saz, Lleida, Marcos, & Canalis, 2006). The ASR system detects the speech input and evaluates the recognition rate of the detected speech; the SPP system then generates the child’s pronunciation score.

View all citing articles on Scopus
View full text