Interpretable Deep Learning Model for the Detection and Reconstruction of Dysarthric Speech
This work addresses the challenge of improving speech quality for individuals with dysarthria, offering a method that enhances detection accuracy and reconstruction, though it appears incremental in its approach.
The paper tackled the problem of detecting and reconstructing dysarthric speech by proposing an encoder-decoder model that factorizes speech into a low-dimensional latent space and text encoding, showing that the latent space conveys interpretable characteristics like intelligibility and fluency, and a MUSHRA perceptual test demonstrated improved fluency in generated speech.
This paper proposed a novel approach for the detection and reconstruction of dysarthric speech. The encoder-decoder model factorizes speech into a low-dimensional latent space and encoding of the input text. We showed that the latent space conveys interpretable characteristics of dysarthria, such as intelligibility and fluency of speech. MUSHRA perceptual test demonstrated that the adaptation of the latent space let the model generate speech of improved fluency. The multi-task supervised approach for predicting both the probability of dysarthric speech and the mel-spectrogram helps improve the detection of dysarthria with higher accuracy. This is thanks to a low-dimensional latent space of the auto-encoder as opposed to directly predicting dysarthria from a highly dimensional mel-spectrogram.