Deep Learning-Based Automatic Speech and Emotion Recognition for Students with Disabilities: A Review

Education is a basic right that enriches the lives of all people. It is a common misconception in education that everyone receives the same benefits and that everyone has an equal chance of success. One of the prevailing ideas is that if students work hard enough, exhibit determination and resilience and take charge of their education and prospects, they can all achieve. Students who have disabilities require support in order to compete successfully. People with hearing loss would greatly benefit from assistive technology by employing VSR and audio-visual speech recognition. The precise meaning of a speaker’s message cannot be determined only by text. In order to comprehend the meaning of speech, it is also vital to consider the speaker’s emotions. In this chapter, state-of-the-art techniques related to automatic speech and emotion recognition models are investigated and how these technologies can aid the education of the physically disabled.