Abstract: A system allows for audio playout of e-book content data using a playout electronic device recorded by a remote recording electronic device. The system may analyse the e-book content to infer XY on-screen display coordinates for each word of the e-book and speech recognition may correlate the timing of the spoken words to the XY coordinates. As such, a read along display animation may be generated by the digital display of the playout electronic device in time with the audio and the respective on-screen position of each word. Eye tracking may be employed by the playout electronic device for the display of a gaze position indicator to the recording electronic device in substantial real-time. The system may further employ machine learning to optimise a trained machine to output at least one prosodic features for user profile specific speech emulation using a speech emulator.

Abstract: A system allows for audio playout of e-book content data using a playout electronic device recorded by a remote recording electronic device. The system may analyse the e-book content to infer XY on-screen display coordinates for each word of the e-book and speech recognition may correlate the timing of the spoken words to the XY coordinates. As such, a read along display animation may be generated by the digital display of the playout electronic device in time with the audio and the respective on-screen position of each word. Eye tracking may be employed by the playout electronic device for the display of a gaze position indicator to the recording electronic device in substantial real-time. The system may further employ machine learning to optimise a trained machine to output at least one prosodic features for user profile specific speech emulation using a speech emulator.