The Datasets analysed were representative of the speech of children with typical development in comparison with those who have speech impairment.
TASK 1 In this repository you will find initial text files of the format 'SLI#.txt' or 'TD#.txt' which are then transformed into 'sli#_cleaned.txt' or 'td#_cleaned.txt'. They are filtered and transformed after the code of task 1 is complete.
TASK 2 Cleaned files are the input of task 2 that are then dissected into 6 statistics. These statistics are found for every single file that was cleaned. Making it in total 20 files.
TASK 3 From the statistics calculated in task 2, the mean of each statistic is to be taken and plotted. This is done for each child group, namely SLI and TD groups, as shown in the notebook.