Towards Identity Preserving Normal to Dysarthric Voice Conversion
Wen-Chin Huang (Nagoya University)
B.M. Halpern (Nederlands Kanker Instituut - Antoni van Leeuwenhoek ziekenhuis, TU Delft - Multimedia Computing, Universiteit van Amsterdam)
Lester Phillip Violeta (Nagoya University)
O.E. Scharenborg (TU Delft - Multimedia Computing)
Tomoki Toda (Nagoya University)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
We present a voice conversion framework that converts normal speech into dysarthric speech while preserving the speaker identity. Such a framework is essential for (1) clinical decision making processes and alleviation of patient stress, (2) data augmentation for dysarthric speech recognition. This is an especially challenging task since the converted samples should capture the severity of dysarthric speech while being highly natural and possessing the speaker identity of the normal speaker. To this end, we adopted a two-stage framework, which consists of a sequence-to-sequence model and a nonparallel frame-wise model. Objective and subjective evaluations were conducted on the UASpeech dataset, and results showed that the method was able to yield reasonable naturalness and capture severity aspects of the pathological speech. On the other hand, the similarity to the normal source speaker’s voice was limited and requires further improvements.