Robust acoustic representation of Japanese vowels under phonation variability using dynamic spectral analysis
- 1School of Japanese Culture and Economics, Xi'an International Studies University, Xi'an, China.
Abstract
Phonation-induced acoustic variability, particularly in whispered speech, poses persistent challenges for stable vowel representation. Conventional static formant-based descriptors often fail to capture the dynamic spectral behavior of vowels under such conditions. This study evaluates the robustness of acoustic feature representations for Japanese vowels across normal and whispered phonation, comparing static formant measures with dynamic spectral features derived from Vowel Inherent Spectral Change (VISC). Dynamic features are used to characterize continuous formant trajectory patterns, while Support Vector Machine (SVM) and Random Forest (RF) classifiers serve as analytical probes to assess representation stability rather than as targets of algorithmic optimization. Results demonstrate that incorporating dynamic spectral information leads to more consistent vowel discrimination across phonation types compared to static-only representations, with similar performance trends observed across classification frameworks. These findings suggest that differences in classification outcomes are primarily driven by properties of the acoustic representations rather than by model choice. The study highlights the im-portance of representation-level design for robust speech signal analysis under phonation-induced variability and supports the use of low-dimensional dynamic features for vowel modeling in variable phonation conditions.
Related
- Acoustic Context Shapes Cortical Encoding of Spectral Discrimination in Normal and Impaired Hearing
- Dual-domain self-supervised feature alignment via spectral–spatial representation learning for deepfake anomaly detection
- Wood spectral variability in Entandrophragma cylindricum across northern Congo: limited association with genetic structure despite high genetic diversity
- Cracking the predictive stability code: dual trial-by-trial spatio-temporo-spectral dynamics of task representation directional tuning by Bayesian conflict expectations
- A representation-level wavelet–EMD fusion framework for spectral analysis and detection of epileptiform patterns in pediatric EEG: computational validation with a roadmap for external benchmarking
BibTeX
@article{zhang2026robust,
title = {{Robust acoustic representation of Japanese vowels under phonation variability using dynamic spectral analysis}},
author = {Yanlong Zhang and Tianxiang Cao and Yueheng Liu},
journal = {PLOS One},
year = {2026},
month = oct,
doi = {10.1371/journal.pone.0361125},
url = {https://doi.org/10.1371/journal.pone.0361125},
note = {CC BY},
}
RIS
TY - JOUR
TI - Robust acoustic representation of Japanese vowels under phonation variability using dynamic spectral analysis
AU - Yanlong Zhang
AU - Tianxiang Cao
AU - Yueheng Liu
PY - 2026
DA - 2026/10/23
JO - PLOS One
DO - 10.1371/journal.pone.0361125
UR - https://doi.org/10.1371/journal.pone.0361125
AB - Phonation-induced acoustic variability, particularly in whispered speech, poses persistent challenges for stable vowel representation. Conventional static formant-based descriptors often fail to capture the dynamic spectral behavior of vowels under such conditions. This study evaluates the robustness of acoustic feature representations for Japanese vowels across normal and whispered phonation, comparing static formant measures with dynamic spectral features derived from Vowel Inherent Spectral Change (VISC). Dynamic features are used to characterize continuous formant trajectory patterns, while Support Vector Machine (SVM) and Random Forest (RF) classifiers serve as analytical probes to assess representation stability rather than as targets of algorithmic optimization. Results demonstrate that incorporating dynamic spectral information leads to more consistent vowel discrimination across phonation types compared to static-only representations, with similar performance trends observed across classification frameworks. These findings suggest that differences in classification outcomes are primarily driven by properties of the acoustic representations rather than by model choice. The study highlights the im-portance of representation-level design for robust speech signal analysis under phonation-induced variability and supports the use of low-dimensional dynamic features for vowel modeling in variable phonation conditions.
SN - 1932-6203
ER -