Related Experiment Video
Updated: Jun 23, 2025
05:48
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
Published on: August 9, 2024
1.5K
Impact of Audio Data Compression on Feature Extraction for Vocal Biomarker Detection: Validation Study
Jessica Oreskovic1, Jaycee Kaufman1, Yan Fossat1
1Klick Labs, Toronto, ON, Canada.
JMIR Biomedical Engineering
|June 14, 2024
Summary
Audio data compression impacts vocal biomarkers, with some features remaining stable across formats. MediaHuman (MH) and FFmpeg converters showed greater resilience, crucial for healthcare applications using compressed voice data.
Area of Science:
- Biomedical Engineering
- Acoustic Analysis
- Digital Signal Processing
Background:
- Vocal biomarkers offer noninvasive medical screening and diagnostics.
- Previous studies showed feasibility of predicting type 2 diabetes mellitus from speech.
- This study investigates audio compression's impact on vocal biomarker development.
Purpose of the Study:
- To analyze how MP3, M4A, and WMA compression affect vocal biomarker features.
- To evaluate the influence of 3 conversion tools and 2 bitrates on feature detection.
- To determine the impact of audio compression on acoustic vocal biomarker development.
Main Methods:
- Compared uncompressed voice samples converted to MP3, M4A, WMA at 320 and 128 kbps.
- Utilized MediaHuman (MH), WonderShare (WS), and FFmpeg conversion tools.
- Extracted features like pitch, jitter, intensity, and Mel-frequency cepstral coefficients (MFCCs) from 17,298 smartphone recordings.
- Applied Wilcoxon signed rank tests and Bonferroni correction for statistical analysis.
Main Results:
- Compression significantly impacted various voice features and MFCCs.
- MediaHuman (MH) converter showed greater resilience than WonderShare (WS).
- Voice features demonstrated greater stability than Mel-frequency cepstral coefficients (MFCCs) across conversion methods.
- Compression effects were feature-specific, with some features consistently altered.
Conclusions:
- Audio compression effects on vocal biomarkers are feature-specific.
- MediaHuman (MH) and FFmpeg converters are more resilient to compression.
- Understanding feature stability is vital for diagnostic applications using compressed voice data.
- Findings support the use of stable vocal features in healthcare applications with compressed audio data.
Related Concept Videos
00:56Extraction: Advanced Methods
446
Metal ions can be separated from one another by complexation with organic ligands–the chelating agent– to form uncharged chelates. Here, the chelating agent must contain hydrophobic groups and behave as a weak acid, losing a proton to bind with the metal. Since most organic ligands used in this process are insoluble or undergo oxidation in the aqueous phase, the chelating agent is initially added to the organic phase and extracted into the aqueous phase. The metal-ligand complex is...
446
01:30Classification of Signals
437
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
437
01:13Sensitivity, Specificity, and Predicted Value
277
In healthcare diagnostics, laboratory tests play a crucial role in identifying and diagnosing a wide range of medical conditions. However, interpreting test results is not always straightforward. An abnormal test result does not always confirm the presence of a disease, just as a normal result does not guarantee its absence. To assess the reliability of these diagnostic tools, healthcare practitioners rely on two key statistical indicators: sensitivity and specificity.
Sensitivity is the...
Sensitivity is the...
277
01:05Difference from Background: Limit of Detection
6.3K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
The LOD indicates the presence or absence...
6.3K