Attentive-based Multi-level Feature Fusion for Voice Disorder Diagnosis

TL;DR

This paper introduces a novel two-stage framework utilizing pre-trained models and an attentive fusion module to improve voice disorder diagnosis accuracy from raw audio, addressing dataset limitations and enhancing feature integration.

Contribution

The study presents a new multi-level feature fusion framework combining ECAPA-TDNN, Wav2vec 2.0, and an attentive module for better voice disorder detection.

Findings

Achieves 90.51% accuracy on FEMH dataset

Outperforms baseline methods in voice disorder classification

Demonstrates effective multi-level feature fusion for diagnosis

Abstract

Voice disorders negatively impact the quality of daily life in various ways. However, accurately recognizing the category of pathological features from raw audio remains a considerable challenge due to the limited dataset. A promising method to handle this issue is extracting multi-level pathological information from speech in a comprehensive manner by fusing features in the latent space. In this paper, a novel framework is designed to explore the way of high-quality feature fusion for effective and generalized detection performance. Specifically, the proposed model follows a two-stage training paradigm: (1) ECAPA-TDNN and Wav2vec 2.0 which have shown remarkable effectiveness in various domains are employed to learn the universal pathological information from raw audio; (2) An attentive fusion module is dedicatedly designed to establish the interaction between pathological features projected by EcapTdnn and Wav2vec 2.0 respectively and guide the multi-layer fusion, the entire model is jointly fine-tuned from pre-trained features by the automatic voice pathology detection task. Finally, comprehensive experiments on the FEMH and SVD datasets demonstrate that the proposed framework outperforms the competitive baselines, and achieves the accuracy of 90.51% and 87.68%.