Hierarchical Multi-Class Classification of Voice Disorders Using Self-Supervised Models and Glottal Features

Abstract

Previous studies on the automatic classification of voice disorders have mostly investigated the binary classification task, which aims to distinguish pathological voice from healthy voice. Using multi-class classifiers, however, more fine-grained identification of voice disorders can be achieved, which is more helpful for clinical practitioners. Unfortunately, there is little publicly available training data for many voice disorders, which lowers the classification performance on data from unseen speakers. Earlier studies have shown that the usage of glottal source features can reduce data redundancy in detection of laryngeal voice disorders. Another approach to tackle the problems caused by scarcity of training data is to utilize deep learning models, such as wav2vec 2.0 and HuBERT, that have been pre-trained on larger databases. Since the aforementioned approaches have not been thoroughly studied in the multi-class classification of voice disorders, they will be jointly studied in the present work. In addition, we study a hierarchical classifier, which enables task-wise feature optimization and more efficient utilization of data. In this work, the aforementioned three approaches are compared with traditional mel frequency cepstral coefficient (MFCC) features and one-vs-rest and one-vs-one SVM classifiers. The results in a 3-class classification problem between healthy voice and two laryngeal disorders (hyperfunctional dysphonia and vocal fold paresis) indicate that all the studied methods outperform the baselines. The best performance was achieved by using features from wav2vec 2.0 LARGE together with hierarchical classification. The balanced classification accuracy of the system was 62.77% for male speakers, and 55.36% for female speakers, which outperformed the baseline systems by an absolute improvement of 15.76% and 6.95% for male and female speakers, respectively.

Convolutional Neural Networks for Classification of Voice Qualities from Speech and Neck Surface Accelerometer Signals

“…The model learns representations from the raw speech, and these representations can be used in the required downstream task. Examples of pre-trained models are wav2vec2 and HuBERT that have shown good performance in various speech technology tasks, such as ASR, emotion recognition, speaker and language identification, and voice disorder detection [47,48,49,50,51,52,53]. There are, however, no studies on using recent self-supervised pre-trained models, such as wav2vec2 [47] and HuBERT [54], for voice quality classification.…”