The Nemours ModelTalker supports voice banking for users diagnosed with ALS/MND and related neurodegenerative diseases. Users record up to 1600 sentences from which a synthetic voice is constructed. For the past two years we have focused on extending and refining a web-based recording tool to support this process. In this demonstration, we illustrate the features of the web-based pipeline that guides patients through the process of setting up to record at home, recording a standard speech inventory, adding custom recordings, and screening alternative versions of their voice and alternative synthesis parameter settings. Finally, we summarize results from 352 individuals with a wide range of speaking ability, who have recently used this voice banking pipeline.
Cite as: Bunnell, H.T., Lilley, J., McGrath, K. (2017) The ModelTalker Project: A Web-Based Voice Banking Pipeline for ALS/MND Patients. Proc. Interspeech 2017, 4032-4033
@inproceedings{bunnell17_interspeech,
author={H. Timothy Bunnell and Jason Lilley and Kathleen McGrath},
title={{The ModelTalker Project: A Web-Based Voice Banking Pipeline for ALS/MND Patients}},
year=2017,
booktitle={Proc. Interspeech 2017},
pages={4032--4033}
}