Multi-class Detection of Pathological Speech with Latent Features

  • The detection of pathologies from speech features is usually defined as a binary classification task with one class representing a specific pathology and the other class representing healthy speech. In this work, we train neural networks, large margin classifiers, and tree boosting machines to distinguish between four pathologies: Parkinson's disease, laryngeal cancer, cleft lip and palate, and oral squamous cell carcinoma. We show that latent representations extracted at different layers of a pre-trained wav2vec 2.0 system can be effectively used to classify these types of pathological voices. We evaluate the robustness of our classifiers by adding room impulse responses to the test data and by applying them to unseen speech corpora. Our approach achieves unweighted average F1-Scores between 74.1% and 97.0%, depending on the model and the noise conditions used. The systems generalize and perform well on unseen data of healthy speakers sampled from a variety of different sources.

Export metadata

Additional Services

Search Google Scholar
Metadaten
Author:Dominik Wagner, Ilja Baumann, Franziska Braun, Sebastian P. BayerlORCiD, Elmar Nöth, Korbinian Riedhammer, Tobias Bocklet
DOI:https://doi.org/10.21437/Interspeech.2023-464
ISSN:2958-1796
Subtitle (English):How does it perform on unseen data?
Document Type:conference proceeding (article)
Language:English
Reviewed:Begutachtet/Reviewed
Release Date:2024/07/08
Pagenumber:5
First Page:2318
Last Page:2322
Konferenzangabe:Annual Conference of the International Speech Communication Association (INTERSPEECH)
institutes:Fakultät Informatik
Licence (German):Keine Lizenz - Deutsches Urheberrecht gilt
Verstanden ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.