Make it possible for users to create their own speech synthesis voices by recording their own voice through a web based interface. The interface prompts the text which is read (which is typically retrieved from Wikipedia) and gives feedback on volume, speech speed etc. To build an understandable HMM speach synthesis voice aprox. 20 min of speech is needed, but more is needed for good quality. Captured speech data can also be used as a basis for a completely free database for speech recognition.
Existing: No
To do: This is not part of MVP and any development happens outside of the scope of this project. Develop the web interface for recording using HTML5 audio and a backend with initial analysis and storage of audio files.
Identified as a component during the pilot study.