Encoder-decoder model with multi-task learning on a low-dimensional latent space improves dysarthria detection accuracy and enables generation of more fluent speech.
The audio and text en- coders produce a low-dimensional dysarthric latent space and a sequential encoding of the input text
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Interpretable Deep Learning Model for the Detection and Reconstruction of Dysarthric Speech
Encoder-decoder model with multi-task learning on a low-dimensional latent space improves dysarthria detection accuracy and enables generation of more fluent speech.