The methodology of developing a Verbal Therapeutic Desktop application for ASD Children

The methodology that we suppose to use throughout this project will be discussed in this article.
When we think about the therapies that can be done for autistic children, Verbal therapies get the highest place. Since they are lack with a developed vocabulary and shows less communication skills in their early childhood, that ability should be improved with the involvement of their parents and therapists.

Here we are suggesting a system that could help ASD children to improve their verbal skills by using an interactive way with the use of technology. As the first step to accomplish the above objective we are going to collect a data set of voice recordings of the autistic children. These data set could be consist of different verbal forms that they trying to express their basic needs. And also a data set of voice recordings of people in order to train the system. We will discuss about that later in this article.
So the collected data set is transformed into a machine understandable way by digitizing each and every signal in order to transform all analog signals into its digital form.

Those digitized signals are then subjected to pre-processing to remove the background noises and to get a sharp audio signal for further processing. For that purpose the pre-processing techniques like different filtering methods are used. By using the pre-processed audio signal the related spectrogram is then obtained for further analysis of the digital signal to find the features and to identify the characteristics of the signal.

The next phase is the speech recognition. The recognition is going to be done using an AI model which is designed to be trained by using different audio signals that are in the data set we collected at the beginning of the project. Here we are going to use deep learning methodologies in order to generate an algorithm that is capable of recognizing the voice signals given by the user. Finally an output will be generated using the probabilistic matching of audio signals by subjecting them to the well trained AI model.

Background- Recent projects for Autism Spectrum Disordered Children

As we mentioned in the earlier article Autism is a major problem nowadays. But if we diagnose this disorder in its earlier stage and if we do proper treatments and training on them, then we can cure this disorder before it gets increased.

In order to that case, many kinds of researches have been done to find solutions with the combination of Technology and Bio-medicine. Those systems aid ASD children in many aspects to enhance their quality of life. In this article, we are going to talk about some brief descriptions of the existing systems that have been developed to improve ASD child's impairments.

L.G Pillai, E.Sherly. A Deep Learning-Based Evaluation of Articulation Disorder and Learning  Assistive System for autistic children. Presented at the International Journal on  Natural Language Computing.

[Online]. Available: https://www.researchgate.net/publication/320926515_A_Deep_Learning_Based_Evaluation_of_Articulation_Disorder_and_Learning_Assistive_System_for_Autistic_Children.  

• The implementation of this work is accomplished through two different stages. In the first stage, they attempted to develop an Automatic Speech Recognition system, to identify the articulation disorder in children with Aspergers’ Syndrome (AS) on the basis of 14 Malayalam vowels. In the second stage, Learning Assistive System for Autistic Child (LASAC)is envisioned to provide speech training as well as impaired speech analysis for Malayalam vowels. A feature vector is used to create the acoustic model and the Euclidean Distance formula is used to analyze the percentage of impairment in AS student’s speech by comparing their speech features against the acoustic model.LASAC provides an interactive interface that offers speech training, speech analysis, and articulation tutorial.

M.Sharda, T.P.Subhadra, S.Sahay, C.Nagaraja, L.Singh, R.Mishra, A.Sen, N.Singhal, D.Erickson, N.C.Singh.Sounds of melody-Pitch patterns of speech in autism. Presented at Neuroscience Letters journal.

[Online].Available:https://www.researchgate.net/publication/44577909_Sounds_of_melody-Pitch_patterns_of_speech_in_autism

• In this research, their objective was to find a pattern in the vocalizations of children with ASD. They have compared the intonational features (pitch patterns of a sentence) of 15 children with ASD,  who speaks, in the 4-10 age group. They have observed exaggerated pitch, pitch range, pitch excursion, and pitch contours in the speech of children with ASD using acoustic measurements.

A.Wojciechowski, R.A.Musawi. Assistive technology application for enhancing social and language skills of young children with autism. Presented at Multimedia Tools and Applications journal.

[Online]. Available: https://link.springer.com/article/10.1007/s11042-016-3995-9

• In there, they have proposed an assistive technology application that is designed for supporting the young children affected by ASD, in their process of learning the pronunciation and meaning of new words. The system was built-up using of a mobile application and object identifiers (Estimate Beacon sensors). The system requires active participation like a parent of the child to select words, record pronunciation of object names, and to activate and turn off the application.

M.Z.A.Aziz, S.A.C.Abdullah, S.F.S.Adnan, L.Mazalan. Educational app for children with Autism Spectrum Disorders (ASDs). Presented at Procedia Computer Science journal.

[Online].Available:https://www.sciencedirect.com/science/article/pii/S1877050914014732

• In there they have developed an application for iOS devices to focus on giving a solution to verbal communication problems. The application will give a new alternative that allows the children to select and choose what they need or what they want to say. And thus avoiding any unwanted miscommunication. Using this application, children with ASD can follow the process of learning by listening to the audio sound after interacting with the picture of the object.

Oller at the LENA Foundation. Researchers seek patterns in the sounds of autism.

[Online]. Available: https://www.spectrumnews.org/news/researchers-seek-patterns-in-the-sounds-of-autism/

• Here they have been used a potential recording device and software algorithm to measure the number and characteristics of sounds emitted from different age groups of children with autism. This research shows that infants make precursors to speech, such as squeals, growls and vowel-like sounds and this study has shown a pattern. These patterns which are not easily detected by the human ear, and require massive computing power to calculate are distinct in children with ASD.

So these are some of the existing researches that have been done on behalf of ASD child's communication problems. So in our project, we proposed to develop a Verbal therapeutic desktop application for Autism disordered children, based on these researches as well as the other related researches.

Verbal Therapeutic Desktop Application for Autism Spectrum Disordered Children

Among us, we have various types of diseases and disabilities which can be cured and cannot be cured by treatments. Some might not be only cured by bio-medicals, but with some psychological perspectives. Autism Spectrum Disorder(ASD) is a neurological and developmental disorder which generally starts appear symptoms in the age of two years and lasts throughout the lifetime. The term ‘Spectrum’ refers because it shows a wide variation in the type and severity of symptoms.

Medical Research Council Social Psychiatry Unit at the Institute of Psychiatry in London demonstrated the clustering of social and communication impairments with lack of pretend play (replaced by repetitive behaviour and interests) has marked autism as a syndrome.

Nature of disabilities of ASD children has described as a triad of Impairments;

1.     Impairment of social interaction

2.     Impairment of verbal and communication

3.     Repetitive behaviour

Each of these impairments should be prescribed at different angles. In the study of this matter we focused on the Impairment of verbal and communication, we found many research papers show that most of the times they have unique abilities and symptoms in linguistic patterns, they speak in an abnormal tone of voice, it is which lead us to re-search their speaking patterns.

With the information we gathered from ASD Therapists, we found that generally, in the age two ASD children show a delay in learning how to speak, repeating the same words or phrases they recently used to listen which someone has just said.

They may respond to a question by asking the same question, they do not understand simple statements or questions. These children have limited ability of successful communication and interaction with others and they struggle with speech and language comprehension, difficulty in communicating needs. So they like to live in their hallucination. They have trouble in moving to different phases in an activity, because of the less comprehension level.

But many children have good memories for information just heard or seen. They have the pictorial in their mind and may develop a strong vocabulary in a particular area of interest very quickly. They are very likely to work with computers and displays.

Making the above fact a plus motivation,

We propose a ‘Verbal Therapeutic Desktop Application for Autism Disordered Children’ to train and enhance their verbal skills and communication skills in an interactive, attractive environment.