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

The detection of pathologies from speech features is usually defined as abinary classification task with one class representing a specific pathology andthe other class representing healthy speech. In this work, we train neuralnetworks, large margin classifiers, and tree boosting machines to distinguishbetween four pathologies: Parkinson's disease, laryngeal cancer, cleft lip andpalate, and oral squamous cell carcinoma. We show that latent representationsextracted at different layers of a pre-trained wav2vec 2.0 system can beeffectively used to classify these types of pathological voices. We evaluatethe robustness of our classifiers by adding room impulse responses to the testdata and by applying them to unseen speech corpora. Our approach achievesunweighted average F1-Scores between 74.1% and 97.0%, depending on the modeland the noise conditions used. The systems generalize and perform well onunseen data of healthy speakers sampled from a variety of different sources.

Multi-class Detection of Pathological Speech with Latent Features: How does it perform on unseen data?