Accepted for/Published in: JMIR Biomedical Engineering
Date Submitted: Jan 10, 2024
Date Accepted: Mar 23, 2024
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Impact of Audio Data Compression on Feature Extraction for Vocal Biomarker Detection
ABSTRACT
Background:
Vocal biomarkers, derived from acoustic analysis of vocal characteristics, offer non-invasive avenues for medical screening, diagnostics, and monitoring. Previous research demonstrated the feasibility of predicting type 2 diabetes mellitus through acoustic analysis of smartphone-recorded speech. This study explores the impact of audio data compression on acoustic vocal biomarker development, critical for broader applicability in healthcare.
Objective:
The objective of this research is to analyze how common audio compression algorithms (MP3, M4A, WMA) at different bitrates, applied by distinct conversion tools (MediaHuman (MH), WonderShare (WS)), affect features crucial for vocal biomarker detection.
Methods:
Acoustic features were extracted from 17298 uncompressed voice samples recorded by 571 participants. Files were converted using MH and WS, applying MP3, M4A, and WMA at 128kbps and 320kbps. Feature extraction involved Python and Parselmouth. Non-parametric statistical analysis assessed the impact of compression on features.
Results:
Non-customizable differences in MH and WS encoders resulted in significant variations in compressed files. P values highlighted feature alterations, revealing feature-specific impacts of compression. Resilient features included meanF0, stdevF0, and rapJitter across various compression methods at specific bitrates. Compression effects were found to be feature-specific, with MH showing greater resilience. Some features were consistently affected, emphasizing the importance of understanding feature resilience for diagnostic applications. Healthcare implications suggest that certain features withstand compression, enabling medical use without compromising accuracy. Focused on specific features and formats, future research could broaden the scope to include diverse features, real-time compression algorithms, and various recording methods.
Conclusions:
This study enhances understanding of audio compression's influence on voice features and MFCCs, providing insights for developing applications across fields. The research underscores the significance of feature resilience in working with compressed audio data, laying a foundation for informed voice data utilization in evolving technological landscapes.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.