Audio-video machine learning regression predicts clinician-rated speech impairment in ALS with a mean RMSE of 0.93 on a 5-25 scale, but without statistically significant benefit over audio alone.
In particular, the best regression model was identified with the SVR, trained using multimodal features, achieving a mRMSE of 0.93 on a scale ranging from 5 to 25
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multimodal Assessment of Speech Impairment in ALS Using Audio-Visual and Machine Learning Approaches
Audio-video machine learning regression predicts clinician-rated speech impairment in ALS with a mean RMSE of 0.93 on a 5-25 scale, but without statistically significant benefit over audio alone.