7.7% of Children in the US have disorders related to voice, speech, language and swallowing. Among them, only 55.2% received appropriate intervention services. Moreover, second-language English learners face even higher barriers to learn English. The challenges include unqualified teachers, the influence of the mother tongue, lack of resources, and lack of motivation. This project aims to bridge this gap by developing a web application that would assist its users to improve their enunciation and their ability to express themselves through speech. The application currently targets children that are either learning a foreign language, or those who have hearing difficulties or speech disorders. The application will guide the users through different levels of difficulties, in which users will practice their speech by repeating sentences that are being displayed on the screen. The speech will be recorded via the device’s microphone, and after audio processing, the sample will be inputted into our deep learning models that will analyze it for any instances of poor clarity. The users will be asked to practice those instances until they are able to correct their speech accordingly. The application will be gamified to motivate children to complete the therapy.
Categories