Organic dysphonia can lead to vocal impairments. Recording patients' impaired voice could allow them to use voice cloning systems. In the domain of speech synthesis, voice cloning is the process of producing speech matching a target speaker voice, given textual input and an audio sample from the speaker. It can achieve high-quality speech with only few data from the target speaker. However, dysphonic patients may only produce speech with specific or limited phonetic content. To our knowledge, the impact of such constraints on a voice cloning system remains to be studied. This article presents the results of preliminary experiments on the matter, along with specifications about the models and datasets used.
Article ID: 2022S03
Publisher: Canadian Artificial Intelligence Association