Acoustic features extracted from the same speech recordings by OpenSMILE, Praat, and Librosa often disagree, with some features showing negative cross-toolkit correlations.
Although end-to-end neural architectures have been in- creasingly adopted, classical feature-based approaches are still widely used
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Comparative Evaluation of Acoustic Feature Extraction Tools for Clinical Speech Analysis
Acoustic features extracted from the same speech recordings by OpenSMILE, Praat, and Librosa often disagree, with some features showing negative cross-toolkit correlations.