Siti Salwah Salim

Artificial neural networks as speech recognisers for dysarthric speech: Identifying the best-performing set of MFCC parameters and studying a speaker-independent approach

Dysarthria is a neurological impairment of controlling the motor speech articulators that compromises the speech signal. Automatic Speech Recognition (ASR) can be very helpful for speakers with dysarthria because the disabled persons are often physically incapacitated. Mel-Frequency Cepstral Coefficients (MFCCs) have been proven to be an appropriate representation of dysarthric speech, but the question of which MFCC-based feature set represents dysarthric acoustic features most effectively has not been answered. Moreover, most of the current dysarthric speech recognisers are either speaker-dependent (SD) or speaker-adaptive (SA), and they perform poorly in terms of generalisability as a speaker-independent (SI) model. First, by comparing the results of 28 dysarthric SD speech recognisers, this study identifies the best-performing set of MFCC parameters, which can represent dysarthric acoustic features to be used in Artificial Neural Network (ANN)-based ASR. Next, this paper studies the application of ANNs as a fixed-length isolated-word SI ASR for individuals who suffer from dysarthria. The results show that the speech recognisers trained by the conventional 12 coefficients MFCC features without the use of delta and acceleration features provided the best accuracy, and the proposed SI ASR recognised the speech of the unforeseen dysarthric evaluation subjects with word recognition rate of 68.38%.

Real-time frequency-based noise-robust Automatic Speech Recognition using Multi-Nets Artificial Neural Networks: A multi-views multi-learners approach

Automatic Speech Recognition (ASR) is a technology for identifying uttered word(s) represented as an acoustic signal. However, one of the important aspects of a noise-robust ASR system is its ability to recognise speech accurately in noisy conditions. This paper studies the applications of Multi-Nets Artificial Neural Networks (M-N ANNs), a realisation of multiple-views multiple-learners approach, as Multi-Networks Speech Recognisers (M-NSRs) in providing a real-time, frequency-based noise-robust ASR model. M-NSRs define speech features associated with each word as a different view and apply a standalone ANN as one of the learners to approximate that view; meanwhile, multiple-views single-learner (MVSL) ANN-based speech recognisers employ only one ANN to memorise the features of the entire vocabulary. In this research, an M-NSR was provided and evaluated using unforeseen test data that were affected by white, brown, and pink noises; more specifically, 27 experiments were conducted on noisy speech to measure the accuracy and recognition rate of the proposed model. Furthermore, the results of the M-NSR were compared in detail with an MVSL ANN-based ASR system. The M-NSR recorded an improved average recognition rate by up to 20.14% when it was given the test data infected with noise in our experiments. It is shown that the M-NSR with higher degree of generalisability can handle frequency-based noise because it has higher recognition rate than the previous model under noisy conditions.

Gamification Solutions to Enhance Software User Engagement—A Systematic Review

ABSTRACT Gamification is the use of video-game mechanics and elements in nongame contexts to enhance user engagement and performance. The purpose of this study is to conduct a systematic review to have an in-depth investigation into the existing gamification solutions targeted at solving user engagement problems in different categories of software. We carried out this systematic review by proposing a framework of gamifying process, which is the basis for comparison of existing gamification solutions. In order to report the review, the primary studies are categorized according to the following: a) gamified software and their platforms; b) elements of the gamifying process; c) gamification solutions in each software type; d) gamification solutions for software user engagement problems; e) gamification solutions in general; and f) effects of gamification on software user engagement and performance. Based on the search procedure and criteria, a total of 78 primary studies were extracted. Most of the studies focused on educational and social software, which were developed for web or mobile platforms. We concluded that the number of studies on motivating users to use software content, solving problems in learning software, and using real identity is very limited. Furthermore, few studies have been carried out on gamifying the following software categories: productivity software, cloud storage, utility software, entertainment software, search engine software, tool software, fitness software, software engineering, information worker software, and health-care software. In addition, a large number of gamification solutions are relatively simple and require improvement. Thus, for future studies, researchers can work on the items discovered in this review; they can improve the quality of the current gamified systems by using a wide variety of game mechanics and interface elements, utilizing a combination of contextual types of rewards and giving users the ability to use received rewards “in-game” and “out-game.”

Problems in requirements engineering education: a survey

Requirements Engineering Education literature presents various problems that students face while taking courses in Requirements Engineering. This paper reports on an exploratory study to assess the present status of the Requirements Engineering course offered in major public universities in Malaysia. The main instrument used to gather data was the questionnaire. 47 responses were received and analyzed. The results from the questionnaire were discussed and compared with the problems presented in Requirements Engineering Education Literature.

Focus Group Discussion Model for Requirements Elicitation Activity

Reviewing existing requirements elicitation models lead to the identification of an environment, detailed activities and tool support are very significant in understanding requirements elicitation activity. The environment ensures involvement from all stakeholders during the requirements elicitation activity in one platform, while the activities are steps that are very important in achieving the goal of requirements elicitation. The support component employs suitable technique that provides platform to groups of stakeholders to participate in requirements elicitation. Emphasizing these three components, in which focus group discussion for requirements elicitation (FGDRE) gives an understanding about the requirements elicitation activity and recommends essential requirements for requirements elicitation tool.

A systematic review of shared visualisation to achieve common ground

This paper reports a systematic review of shared visualisation based on fifteen papers from 2000 to 2013. The findings identified five shared visualisation strategies that represent the ways implemented to process data sharing and knowledge to arrive at the desired level of understanding. Four visualisation techniques were also identified to show how shared cognition is made possible in designing tools for mediating data or knowledge among the users involved. These findings provide research opportunities in integrating rich interactive data visualisation for mobile-based technologies as an effective mean in supporting collaborative work. Finally, social, task and cognitive elements which can be significantly supported by shared visualisation and a guideline for future researchers seeking to design shared visualisation-based systems are presented. We conducted a systematic review of shared visualisation for shared cognition.We have identified 9 shared visualisation strategies and techniques.These strategies, techniques are capable to provide social, task, cognitive support.The findings of this review suggest a guide for shared visualization design.

A Multi-Views Multi-Learners Approach Towards Dysarthric Speech Recognition Using Multi-Nets Artificial Neural Networks

Automatic speech recognition (ASR) can be very helpful for speakers who suffer from dysarthria, a neurological disability that damages the control of motor speech articulators. Although a few attempts have been made to apply ASR technologies to sufferers of dysarthria, previous studies show that such ASR systems have not attained an adequate level of performance. In this study, a dysarthric multi-networks speech recognizer (DM-NSR) model is provided using a realization of multi-views multi-learners approach called multi-nets artificial neural networks, which tolerates variability of dysarthric speech. In particular, the DM-NSR model employs several ANNs (as learners) to approximate the likelihood of ASR vocabulary words and to deal with the complexity of dysarthric speech. The proposed DM-NSR approach was presented as both speaker-dependent and speaker-independent paradigms. In order to highlight the performance of the proposed model over legacy models, multi-views single-learner models of the DM-NSRs were also provided and their efficiencies were compared in detail. Moreover, a comparison among the prominent dysarthric ASR methods and the proposed one is provided. The results show that the DM-NSR recorded improved recognition rate by up to 24.67% and the error rate was reduced by up to 8.63% over the reference model.

Investigating cognitive task difficulties and expert skills in e-Learning storyboards using a cognitive task analysis technique

E-learning storyboards have been a useful approach in distance learning development to support interaction between instructional designers and subject-matter experts. Current works show that researchers are focusing on different approaches for use in storyboards, and there is less emphasis on the effect of design and process difficulties faced by instructional designers and subject-matter experts. This study explores problem aspects of the cognitive task and the skills required of subject-matter experts by applying a cognitive task analysis approach from the expert point of view. The result shows that subject-matter experts face difficulties in making decisions on three elements during e-learning course development. The three elements are storyboard templates, prescriptive interactive components, and review process. It is found that the representation skills and decision making of the three elements allows subject-matter experts to decide on alternatives of the task process. The result also indicates that it is important to leverage the design and process skills of subject-matter experts as it affects their interaction with instructional designers. Three recommendations are made: training development, prescriptive interactive components development, and interaction design document development. A new framework can be recommended to train subject-matter experts as e-learning storyboard users, and in turn provide for effective interaction between them and instructional designers.

Exploring the influence of general and specific factors on the recognition accuracy of an ASR system for dysarthric speaker

Reviewed existing literature on the performance of ASR system for dysarthria.Analysed influence of speech/speaker mode, vocabulary size & speaking style on WER.Identified specific factors of Dysarthric speech on WER.Analysed influence of specific factor on WER.Measured the correlation of general and specific factors on WER. Automatic speech recognition (ASR) is becoming an important assistive tool among the speech impaired individuals such as dysarthria. Currently, the existing ASR systems were unable to recognise dysarthric speech at an acceptable degree. Little research was carried out to identify factors that influence the performance of ASR system in recognising dysarthric speech. This article aims to identify factors that potentially influence the recognition accuracy of ASR system in recognising dysarthric speech. Some of the factors that influence the recognition accuracy of ASR, which have been confirmed in existing researches for ASR system are speech mode, speaker mode, vocabulary size and speaking styles. We have also focused at factors that are more specific to dysarthric speech such as speech intelligibility, severity and intra-speaker variability that potentially influence the recognition accuracy. We have evaluated the influence of these factors on recognition accuracy using data published in existing researches. It was found that general factors considered in this review have little influence on the recognition accuracy. However, factors more specific to dysarthric speech were found to have a significant influence on the recognition accuracy of the ASR system. From the findings, it can be concluded that intelligibility and severity have significant influence on the recognition accuracy. To improve the recognition accuracy of ASR system, methods and techniques that reduces the influence of these specific factors should be identified.

Studying relevant socio-technical aspects of requirements-driven collaboration in agile teams

Requirements engineering requires intensive collaboration among team members. Agile methods also require constant collaboration among those involved in the project. While working on certain interdependent tasks, team members develop social and technical relationships that instigate socio-technical dependencies. The main goal of our research is to investigate socio-technical aspects that underlie requirements-driven collaboration among agile teams and their influence on project performance. In this paper we present our research approach to achieve such goal and briefly report on preliminary findings. A survey revealed that communication and awareness are the most relevant socio-technical aspects that underlie requirements-driven collaboration in agile teams. Initial findings of a case study aiming to identify requirements-driven collaboration patterns suggest that teams well aware of each other have lesser communication gaps and require lesser rework. Findings will contribute to a better understanding of the relationship between collaboration and performance in agile teams.