Speaker Embeddings as Individuality Proxy for Voice Stress Detection
This work addresses voice stress detection for applications like health monitoring or security, but it is incremental as it builds on prior methods by adding speaker-specific adjustments.
The paper tackled the problem of detecting voice stress across different languages and stress types by incorporating speaker embeddings into existing audio features, resulting in significant performance improvements with only 3-5 seconds of audio input.
Since the mental states of the speaker modulate speech, stress introduced by cognitive or physical loads could be detected in the voice. The existing voice stress detection benchmark has shown that the audio embeddings extracted from the Hybrid BYOL-S self-supervised model perform well. However, the benchmark only evaluates performance separately on each dataset, but does not evaluate performance across the different types of stress and different languages. Moreover, previous studies found strong individual differences in stress susceptibility. This paper presents the design and development of voice stress detection, trained on more than 100 speakers from 9 language groups and five different types of stress. We address individual variabilities in voice stress analysis by adding speaker embeddings to the hybrid BYOL-S features. The proposed method significantly improves voice stress detection performance with an input audio length of only 3-5 seconds.