Task: Add models/pipelines for extracting Rate of speech metrics

sensein / senselab

senselab is a Python package that simplifies building pipelines for biometric (e.g. speech, voice, video, etc) analysis.

http://sensein.group/senselab/

Apache License 2.0

10 stars 3 forks source link

Task: Add models/pipelines for extracting Rate of speech metrics #155

Open 900miles opened 2 months ago

900miles commented 2 months ago

Description

This is for the Automating the MSE project.

Clinical Observation	Observation Sub-Components	Potential Features + Approaches
Speed		Mean length of clause, T-units per sentence, Verbal Rate, Articulation Rate
Pauses		Length of pauses, Standardized Pause Rate, Pause Duration mean, Total number of pauses, Pause variability
Pressured Speech		T‐units per sentence, BERT surprisal sum, Mean length of sentence,Type‐token ratio

Tasks

See above

Freeform Notes

No response

ibevers commented 2 months ago

@900miles What is the MSE project?

900miles commented 2 months ago

A project intending to automate aspects of the Mental Status Exam (MSE) using biometric data. For example, this issue would intend to use audio data to determine the patient's speed, pauses, and pressured speech aspects of the "speech" part of the MSE automatically.

fabiocat93 commented 6 days ago

@900miles can you please move this discussion to the issue https://github.com/orgs/sensein/projects/45/views/4?pane=issue&itemId=87451216&issue=sensein%7Csenselab%7C193 and keep working from the linked branch?