arXiv:2511.09702v2 Announce Type: replace-cross 
Abstract: Phonotrauma refers to vocal fold tissue damage resulting from exposure to forces during voicing. It occurs on a continuum from mild to severe, and treatment options can vary based on severity. Assessment of severity involves a clinician's expert judgment, which is costly and can vary widely in reliability. In this work, we present the first method for automatically classifying phonotrauma severity from vocal fold images. To account for the ordinal nature of the labels, we adopt a widely used ordinal regression framework. To account for label uncertainty, we propose a novel modification to ordinal regression loss functions that enables them to operate on soft labels reflecting annotator rating distributions. Our proposed soft ordinal regression method achieves predictive performance approaching that of clinical experts, while producing well-calibrated uncertainty estimates. By providing an automated tool for phonotrauma severity assessment, our work can enable large-scale studies of phonotrauma, ultimately leading to improved clinical understanding and patient care.

تم تطوير طريقة جديدة لتصنيف شدة الفونوتروما تلقائيًا، والتي تشير إلى تلف أنسجة الحبال الصوتية الناتج عن التعرض للقوى أثناء الصوت. تستخدم هذه الطريقة صور الحبال الصوتية وإطار الانحدار الترتيبي لتقييم الشدة، مما يعالج التحديات المتعلقة بتباين حكم الخبراء وتكاليفه في البيئات السريرية.

Se ha desarrollado un nuevo método para clasificar automáticamente la gravedad del fonotrauma, que se refiere al daño en los tejidos de las cuerdas vocales causado por fuerzas durante la fonación. Este método utiliza imágenes de las cuerdas vocales y un marco de regresión ordinal para evaluar la gravedad, abordando los desafíos de la variabilidad del juicio experto y el costo en entornos clínicos.

Une nouvelle méthode a été développée pour classer automatiquement la gravité du phonotrauma, qui désigne les lésions des tissus des cordes vocales causées par des forces lors de la phonation. Cette méthode utilise des images des cordes vocales et un cadre de régression ordinale pour évaluer la gravité, répondant aux défis de la variabilité et du coût du jugement des experts en milieu clinique.

A new method has been developed for automatically classifying the severity of phonotrauma, which refers to vocal fold tissue damage caused by voicing forces. This method utilizes vocal fold images and an ordinal regression framework to assess severity, addressing the challenges of expert judgment variability and cost in clinical settings.

Classifying Phonotrauma Severity from Vocal Fold Images with Soft Ordinal Regression

Was this article worth reading? Share it

vidvoi

Usercall

SoundWise.ai

OpenL Translator

Com.locatelloapp

Summify

Ready to build your own newsroom?