Detecting Vocal Fatigue with Neural Embeddings
This addresses the problem of monitoring vocal health for speakers or professionals who use their voice extensively, but it is incremental as it applies existing neural embeddings to a specific domain.
This paper tackled the problem of detecting vocal fatigue, which is the feeling of tiredness in voice from extended use, by comparing neural embeddings like x-vectors, ECAPA-TDNN, and wav2vec 2.0 on academic spoken English data, achieving accuracy scores of 81%, 85%, and 82% respectively after 50 minutes of speaking with temporal smoothing and normalization.
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.