Variability of speech timing features across repeated recordings: a comparison of open-source extraction techniques

Judith Dineley, Ewan Carr, Lauren White, Catriona Lucas, Zahia Rahman, Tian Pan, Faith Matcham, Johnny Downs, Richard Dobson, Thomas F. Quatieri, Nicholas Cummins

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

Abstract

Variations in speech timing features have been reliably linked to symptoms of various health conditions, demonstrating clinical potential. However, replication challenges hinder their translation; extracted speech features are susceptible to methodological variations in the recording and processing pipeline. Investigating this, we compared exemplar timing features extracted via three different techniques from recordings of healthy speech. Our results show that features extracted via an intensity-based method differ from those produced by forced alignment. Different extraction methods also led to differing estimates of within-speaker feature variability over time in an analysis of recordings repeated systematically over three sessions in one day (n=26) and in one week (n=28). Our findings highlight the importance of feature extraction in study design and interpretation, and the need for consistent, accurate extraction techniques for clinical research.
Original languageEnglish
Title of host publicationISCA Archive
PublisherInternational Speech Communication Association
Pages2015-2019
Number of pages5
Volume2024-August
DOIs
Publication statusPublished - 1 Sept 2024

Keywords

  • speech timing
  • feature extraction
  • reproducibility
  • longitudinal monitoring
  • health

Fingerprint

Dive into the research topics of 'Variability of speech timing features across repeated recordings: a comparison of open-source extraction techniques'. Together they form a unique fingerprint.

Cite this