English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Acoustic-to-articulatory inversion (AAI) involves mapping from the acousticto the articulatory space. Signal-processing features like the MFCCs, have beenwidely used for the AAI task. For subjects with dysarthric speech, AAI ischallenging because of an imprecise and indistinct pronunciation. In this work,we perform AAI for dysarthric speech using representations from pre-trainedself-supervised learning (SSL) models. We demonstrate the impact of differentpre-trained features on this challenging AAI task, at low-resource conditions.In addition, we also condition x-vectors to the extracted SSL features to traina BLSTM network. In the seen case, we experiment with three AAI trainingschemes (subject-specific, pooled, and fine-tuned). The results, consistentacross training schemes, reveal that DeCoAR, in the fine-tuned scheme, achievesa relative improvement of the Pearson Correlation Coefficient (CC) by ~1.81%and ~4.56% for healthy controls and patients, respectively, over MFCCs. Weobserve similar average trends for different SSL features in the unseen case.Overall, SSL networks like wav2vec, APC, and DeCoAR, trained with featurereconstruction or future timestep prediction tasks, perform well in predictingdysarthric articulatory trajectories.

Acoustic-to-articulatory inversion for dysarthric speech: Are pre-trained self-supervised representations favorable?