My-Own-Voice: A Web Service That Allows You to Create a Text-to-Speech Voice From Your Own Voice

My-Own-Voice is a service that provides a tool to end-users who want to have their voices synthesized by a high-quality commercial-grade Text-to-Speech system without the need to install, configure or manage speech-processing software and equipment. The system records and validates users’ utterances with Automatic Speech Recognition (ASR), to build an HMM or a Unit Selection synthetic voice. All the procedures are automated to avoid human intervention. We describe here the system for particular end-users about to lose the ability to speak with their own voice, who can now synthetically recreate it with the help of their speech therapist, enabling them to preserve this essential part of their identity.