Harmonic-Percussive Source Separation Versus Multi-Condition Training Set for Robust Speaker Verification in Adverse Acoustic Environments: Viability Study and Best Practices
Year: 2026
Type: article
Abstract: Speaker Recognition (SR) systems suffer from severe performance degradation when deployed in real-world environments with ambient noise and reverberation. This study investigates a joint harmonic-percussive feature representation, combining RASTA-MFCC descriptors extracted independently from both harmonic and percussive streams that help to manage noise in classical machine learning classifiers (SVM, Random Forest, Naïve Bayes), and compares them with the deep embedding extractor ECAPA-TDNN. Evaluated on the VOiCES dataset across diverse room geometries and background distractors, our results demonstrate that while deep neural models handle adverse acoustics natively, HPPS provides a consistent performance boost for classical ML pipelines with a decrement of the error rate up to 5% on weighted mean error and 8% on specific noises as television, highlighting a viable mechanism for enhancing robustness at the expense of additional computational overhead.
Source: Information
DOI: 10.3390/info17111121
Institutions: University of Rome Tor Vergata, University of Palermo
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,930
OpenAlex ID: W7225658310
FWCI:
Cites:
Cited by:
Related to: