Speech prosody as a biosignal for physical pain detection

Abstract

Obtaining an objective assessment of pain is an important challenge for clinicians. The purpose of this study is to examine the connections between subjective reports of pain and measureable biosignals of human speech prosody, as a step towards coping with this challenge. Patients reporting pain were voice-recorded to attain reports on different levels of pain. Recording was done in the patients' natural environment at the medical center. Features were extracted from the voice-recordings, including features that were exclusively developed for this study. A machine-learning based classification process was performed in order to distinguish between samples with "no significant pain" and with "significant pain" reported. This classification process distinguished well between the two categories. Moreover, features developed during this study improved classification results in comparison to classification based solely on knownfeatures. Results indicate that there is evidence of a connection between measureable biosignal parameters of speech and the simultaneous self-reported pain level. This finding might be useful for developing future methods to more objective assessment of pain.

Phonetic characteristics of vocalizations during pain

“…Regression analyses reflecting the association between phonetic characteristics and self-report ratings revealed that only the phonetic changes from thermoception to nociception (when considering “u” and “schwa”) could predict changes in the pain experience. Oshrat et al 12 also concluded from their phonetic analysis that distinguishing pain from no pain is easier than differentiating pain levels. Such conclusions fit in with previous findings on the facial expression of pain, where facial expressions help to predict self-report ratings when considering changes across different pain intensities.…”

COVID-19 and Computer Audition: An Overview on What Speech & Sound Analysis Could Contribute in the SARS-CoV-2 Corona Crisis

“…The assessment of sleepiness—a further symptom of COVID-19—was first featured in ComParE in 2011 ( 11 ) as binary task, and as continuous sleepiness assessment on the Karolinska sleepiness scale in 2019 ( 9 ). Also pain such as headache or bodily pain can accompany COVID-19; speech under pain has also been shown to be automatically accessible ( 12 , 13 ). When it comes to individual risk assessment and monitoring, speaker traits may be of interest.…”

Computer Audition for Fighting the SARS-CoV-2 Corona Crisis—Introducing the Multitask Speech Corpus for COVID-19

“…In the ongoing COMPARE 2020 challenge, continuous assessment of breathing patterns are proposed [26]. Moreover, automatically recognising speech under a pain symptom [27], [28] could be useful for an early warning. It is also found that, COVID-19 patients should have a lack of appetite [29], which can be detected via the eating behaviour analysis while speaking [30].…”