Detecting Vocal Fatigue with Neural Embeddings

TL;DR

This study demonstrates that neural embeddings like x-vectors, ECAPA-TDNN, and wav2vec 2.0 can reliably detect vocal fatigue from spoken English within 50 minutes, achieving high accuracy across speakers and environments.

Contribution

It introduces a method using neural embeddings and support vector machines for early detection of vocal fatigue with high accuracy.

Findings

ECAPA-TDNN achieved 85% accuracy.

Detection is reliable after only 50 minutes of speech.

System maintains 76% accuracy across different speakers and environments.

Abstract

Vocal fatigue refers to the feeling of tiredness and weakness of voice due to extended utilization. This paper investigates the effectiveness of neural embeddings for the detection of vocal fatigue. We compare x-vectors, ECAPA-TDNN, and wav2vec 2.0 embeddings on a corpus of academic spoken English. Low-dimensional mappings of the data reveal that neural embeddings capture information about the change in vocal characteristics of a speaker during prolonged voice usage. We show that vocal fatigue can be reliably predicted using all three kinds of neural embeddings after only 50 minutes of continuous speaking when temporal smoothing and normalization are applied to the extracted embeddings. We employ support vector machines for classification and achieve accuracy scores of 81% using x-vectors, 85% using ECAPA-TDNN embeddings, and 82% using wav2vec 2.0 embeddings as input features. We obtain an accuracy score of 76%, when the trained system is applied to a different speaker and recording environment without any adaptation.