TAME Pain data release: using audio signals to characterize pain

Abstract

Accurately assessing pain through speech remains a challenge in medical practice, with profound implications for patient care and health outcomes. This paper presents a comprehensive dataset that captures the relationship between induced acute pain and speech in adults. We utilized the Cold Pressor Task (CPT) method to induce pain and recorded over 7,000 utterances from 51 participants, correlating their self-reported pain levels with vocal cues. This dataset stands as the largest of its kind to date and includes comprehensive annotations detailing background noise, speech errors, and non-speech vocal features.

Links

• Paper Link