MyMedR

Displaying all 3 publications

Abstract:

Sort:

Fulltext Heuristics to Evaluate Interactive Systems for Children with Autism Spectrum Disorder (ASD)

Khowaja K, Salim SS, Asemi A

PLoS One, 2015;10(7):e0132187.
PMID: 26196385 DOI: 10.1371/journal.pone.0132187

In this paper, we adapted and expanded a set of guidelines, also known as heuristics, to evaluate the usability of software to now be appropriate for software aimed at children with autism spectrum disorder (ASD). We started from the heuristics developed by Nielsen in 1990 and developed a modified set of 15 heuristics. The first 5 heuristics of this set are the same as those of the original Nielsen set, the next 5 heuristics are improved versions of Nielsen's, whereas the last 5 heuristics are new. We present two evaluation studies of our new heuristics. In the first, two groups compared Nielsen's set with the modified set of heuristics, with each group evaluating two interactive systems. The Nielsen's heuristics were assigned to the control group while the experimental group was given the modified set of heuristics, and a statistical analysis was conducted to determine the effectiveness of the modified set, the contribution of 5 new heuristics and the impact of 5 improved heuristics. The results show that the modified set is significantly more effective than the original, and we found a significant difference between the five improved heuristics and their corresponding heuristics in the original set. The five new heuristics are effective in problem identification using the modified set. The second study was conducted using a system which was developed to ascertain if the modified set was effective at identifying usability problems that could be fixed before the release of software. The post-study analysis revealed that the majority of the usability problems identified by the experts were fixed in the updated version of the system.
A speech pronunciation practice system for speech-impaired children: A study to measure its success

Salim SS, Mustafa MB, Asemi A, Ahmad A, Mohamed N, Ghazali KB

Res Dev Disabil, 2016 Sep;56:41-59.
PMID: 27262125 DOI: 10.1016/j.ridd.2016.05.013

BACKGROUND: The speech pronunciation practice (SPP) system enables children with speech impairments to practise and improve their speech pronunciation. However, little is known about the surrogate measures of the SPP system.
AIMS: This research aims to measure the success and effectiveness of the SPP system using three surrogate measures: usage (frequency of use), performance (recognition accuracy) and satisfaction (children's subjective reactions), and how these measures are aligned with the success of the SPP system, as well as to each other.
METHODS AND PROCEDURES: We have measured the absolute change in the word error rate (WER) between the pre- and post-training, using the ANOVA test. Correlation co-efficiency (CC) analysis was conducted to test the relation between the surrogate measures, while a Structural Equation Model (SEM) was used to investigate the causal relations between the measures.
OUTCOMES AND RESULTS: The CC test results indicate a positive correlation between the surrogate measures. The SEM supports all the proposed gtheses. The ANOVA results indicate that SPP is effective in reducing the WER of impaired speech.
CONCLUSIONS AND IMPLICATIONS: The SPP system is an effective assistive tool, especially for high levels of severity. We found that performance is a mediator of the relation between "usage" and "satisfaction".
Fulltext Severity-based adaptation with limited data for ASR to aid dysarthric speakers

Mustafa MB, Salim SS, Mohamed N, Al-Qatab B, Siong CE

PLoS One, 2014;9(1):e86285.
PMID: 24466004 DOI: 10.1371/journal.pone.0086285

Automatic speech recognition (ASR) is currently used in many assistive technologies, such as helping individuals with speech impairment in their communication ability. One challenge in ASR for speech-impaired individuals is the difficulty in obtaining a good speech database of impaired speakers for building an effective speech acoustic model. Because there are very few existing databases of impaired speech, which are also limited in size, the obvious solution to build a speech acoustic model of impaired speech is by employing adaptation techniques. However, issues that have not been addressed in existing studies in the area of adaptation for speech impairment are as follows: (1) identifying the most effective adaptation technique for impaired speech; and (2) the use of suitable source models to build an effective impaired-speech acoustic model. This research investigates the above-mentioned two issues on dysarthria, a type of speech impairment affecting millions of people. We applied both unimpaired and impaired speech as the source model with well-known adaptation techniques like the maximum likelihood linear regression (MLLR) and the constrained-MLLR(C-MLLR). The recognition accuracy of each impaired speech acoustic model is measured in terms of word error rate (WER), with further assessments, including phoneme insertion, substitution and deletion rates. Unimpaired speech when combined with limited high-quality speech-impaired data improves performance of ASR systems in recognising severely impaired dysarthric speech. The C-MLLR adaptation technique was also found to be better than MLLR in recognising mildly and moderately impaired speech based on the statistical analysis of the WER. It was found that phoneme substitution was the biggest contributing factor in WER in dysarthric speech for all levels of severity. The results show that the speech acoustic models derived from suitable adaptation techniques improve the performance of ASR systems in recognising impaired speech with limited adaptation data.

Filters

Please provide feedback to Administrator ([email protected])

External Links