What type of study is this?

This is a Quantitative Study study.

October 12, 2025Open Access

Automated Severity and Breathiness Assessment of Disordered Speech Using a Speech Foundation Model

View Full Paper

Ask AI

Bookmark

Authors

Novel model evaluates dysphonia severity and breathiness in audio samples, highlighting ASR and feature mapping techniques.

The automated speech quality model demonstrates superior accuracy in predicting dysphonia severity and breathiness.
Validation against state-of-the-art methods confirms enhanced generalization across diverse audio samples.
The integration of ASR embeddings with deep feature mapping significantly improves perceptual speech quality assessments.
The use of long-range dependencies captured by attention networks further refines temporal dynamics in speech analysis.

Ashkanichenarlogh et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark