Comparative Evaluation of Acoustic Feature Extraction Tools for Clinical Speech Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911108710793216 |
|---|---|
| author | Choi, Anna Seo Gyeong Richardson, Alexander Partlan, Ryan Tang, Sunny Cho, Sunghye |
| author_facet | Choi, Anna Seo Gyeong Richardson, Alexander Partlan, Ryan Tang, Sunny Cho, Sunghye |
| contents | This study compares three acoustic feature extraction toolkits (OpenSMILE, Praat, and Librosa) applied to clinical speech data from individuals with schizophrenia spectrum disorders (SSD) and healthy controls (HC). By standardizing extraction parameters across the toolkits, we analyzed speech samples from 77 SSD and 87 HC participants and found significant toolkit-dependent variations. While F0 percentiles showed high cross-toolkit correlation (r=0.962 to 0.999), measures like F0 standard deviation and formant values often had poor, even negative, agreement. Additionally, correlation patterns differed between SSD and HC groups. Classification analysis identified F0 mean, HNR, and MFCC1 (AUC greater than 0.70) as promising discriminators. These findings underscore reproducibility concerns and advocate for standardized protocols, multi-toolkit cross-validation, and transparent reporting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01129 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Comparative Evaluation of Acoustic Feature Extraction Tools for Clinical Speech Analysis Choi, Anna Seo Gyeong Richardson, Alexander Partlan, Ryan Tang, Sunny Cho, Sunghye Sound Audio and Speech Processing This study compares three acoustic feature extraction toolkits (OpenSMILE, Praat, and Librosa) applied to clinical speech data from individuals with schizophrenia spectrum disorders (SSD) and healthy controls (HC). By standardizing extraction parameters across the toolkits, we analyzed speech samples from 77 SSD and 87 HC participants and found significant toolkit-dependent variations. While F0 percentiles showed high cross-toolkit correlation (r=0.962 to 0.999), measures like F0 standard deviation and formant values often had poor, even negative, agreement. Additionally, correlation patterns differed between SSD and HC groups. Classification analysis identified F0 mean, HNR, and MFCC1 (AUC greater than 0.70) as promising discriminators. These findings underscore reproducibility concerns and advocate for standardized protocols, multi-toolkit cross-validation, and transparent reporting. |
| title | Comparative Evaluation of Acoustic Feature Extraction Tools for Clinical Speech Analysis |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2506.01129 |