Real Time Speech and Emotions Assistant

Facial expression, vocal tone and timing are some of the most important attributes to public speaking skills. Under high pressure events that involve speaking such as interviews or presentations, many are bound to make mistakes that they might not be aware of. For example, their nervousness will turn their smiles upside down, awkward pacing of speech and tone variations that betray their true intention. Hence, incorporating 3 supervised machine learning models, facial emotion detection, speech tone detection and speech cadence detection, Real time Speech Assistant provides the ability to take in a live video of a user and notify them if they are not showing appropriate facial expression, not varying their tone enough or pacing of speech.

poster

Description

Facial expression, vocal tone and timing are some of the most important attributes to public speaking skills. Under high pressure events that involve speaking such as interviews or presentations, many are bound to make mistakes that they might not be aware of. For example, their nervousness will turn their smiles upside down, awkward pacing of speech and tone variations that betray their true intention. Hence, incorporating 3 supervised machine learning models, facial emotion detection, speech tone detection and speech cadence detection, Real time Speech Assistant provides the ability to take in a live video of a user and notify them if they are not showing appropriate facial expression, not varying their tone enough or pacing of speech.