The current text to speech systems that are available tend to be very limiting, only allowing for a limited selection of voices, most which would better fit in a sci-fi thriller. While text to speech programs have come a long way, they still are very limiting, making for an uncomfortable experience for people expecting a familiar voice when answering the phone.
By extracting specific syllables out of words, we are trying to make a quick text to speech program that can use a person's own voice, instead of a robot's voice. This has many applications, including restoring someone's actual voice (useful in cases where they have lost it completely) or making robocalls more friendly for everyone.
Log in or sign up for Devpost to join the conversation.