Comparison of Acoustic and Textual Features for Dysarthria Severity Classification in Amyotrophic Lateral Sclerosis

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F26%3A0201584" target="_blank" >RIV/00216305:26230/26:0201584 - isvavai.cz</a>
Result on the web
<a href="https://www.isca-archive.org/interspeech_2025/ys25_interspeech.pdf" target="_blank" >https://www.isca-archive.org/interspeech_2025/ys25_interspeech.pdf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.21437/Interspeech.2025-2767" target="_blank" >10.21437/Interspeech.2025-2767</a>

Result language
angličtina
Original language name
Comparison of Acoustic and Textual Features for Dysarthria Severity Classification in Amyotrophic Lateral Sclerosis
Original language description
We explore language-agnostic deep text embeddings for severity classification of dysarthria in Amyotrophic Lateral Sclerosis (ALS). Speech recordings are transcribed by human and ASR and embeddings of the transcripts are considered. Though speech recognition accuracy has been studied for grading dysarthria severity, no effort has yet been made to utilize text embeddings of the transcripts. We perform severity classification at different granularity (2, 3, and 5-class) using data obtained from 47 ALS subjects. Experiments with dense neural network based classifiers suggest that, though text features achieve nearly equal performances as baseline speech features, like statistics of mel frequency cepstral coefficients (MFCC), for 2-class classification, speech features outperform for higher number of classes. Concatenation of text embeddings and MFCC statistics attains the best performances with mean F1 scores of 88%, 68%, and 53%, respectively, in 2, 3, and 5-class classification.
Czech name
—
Czech description
—

Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
ISBN
—
ISSN
—
e-ISSN
2308-457X
Number of pages
5
Pages from-to
803-807
Publisher name
Isca-Int Speech Communication Assoc
Place of publication
Rotterdam, The Netherlands
Event location
Rotterdam
Event date
Aug 17, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
001585350500166

Similar results(10)