Speech and voice acoustic analysis represents an emerging objective diagnostic tool for corticobasal syndrome (CBS), leveraging quantitative measures of speech production to distinguish CBS from other atypical parkinsonian disorders. While clinical speech evaluation has long been part of the neurological assessment, machine learning-based acoustic analysis can achieve high diagnostic accuracy for differentiating corticobasal degeneration (CBD) from progressive supranuclear palsy (PSP) and Parkinson's disease (PD)[1].
CBS presents with a distinctive speech profile that differs from PSP and PD:
However, traditional clinical assessment relies on subjective listener judgment. Acoustic analysis provides objective, quantifiable biomarkers that can:
Recent studies demonstrate that machine learning algorithms applied to speech samples can distinguish CBD from PSP/PD with up to 92% accuracy[1:1]. This approaches the accuracy of more invasive or expensive diagnostic methods.
Description: The base frequency of the vocal fold vibration, perceived as pitch.
CBS-specific findings:
Measurement: Extracted using software like Praat, VoiceSauce, or built-in smartphone algorithms.
Description: Resonant frequencies of the vocal tract that shape vowel quality.
CBS-specific findings:
Clinical relevance: Formant analysis can detect subtle apraxia of speech even when clinical examination is equivocal.
Description: Cycle-to-cycle variation in fundamental frequency, reflecting vocal fold instability.
CBS-specific findings:
Formula:
Description: Cycle-to-cycle variation in amplitude, reflecting vocal fold closure irregularities.
CBS-specific findings:
Formula:
Description: Ratio of harmonic energy to noise in the voice signal.
CBS-specific findings:
Description: Quantification of articulation rate, pause frequency, and pause duration.
CBS-specific findings:
| Acoustic Feature | CBS | PSP | PD |
|---|---|---|---|
| Jitter | Markedly elevated | Moderately elevated | Mildly elevated |
| Shimmer | Elevated | Moderate | Mild |
| F0 variability | High | Moderate | Low |
| Formant precision | Impaired (AOS) | Preserved | Preserved |
| Speech rate | Slow, irregular | Slow, regular | Normal to slow |
| HNR | Reduced | Reduced | Preserved early |
Apraxia of Speech Signature in CBS
PSP Pattern
PD Pattern
Clinical tip: The combination of formant imprecision + elevated jitter strongly suggests CBS over PSP/PD[4].
Time-domain:
Frequency-domain:
Prosodic:
| Algorithm | Performance | Notes |
|---|---|---|
| Random Forest | ~88-92% accuracy | Good for feature importance analysis |
| Support Vector Machine (SVM) | ~85-90% | Effective with limited data |
| Neural Networks | ~90-95% | Requires larger datasets |
| Gradient Boosting | ~87-92% | Robust to overfitting |
| Platform | Features | Validation |
|---|---|---|
| Voicewise | Cloud-based analysis, HIPAA compliant | [6] |
| mPower (Apple) | Research platform, large dataset | Parkinson disease focused |
| Kardia | Passive monitoring, voice tasks | Cardiac, adaptable |
| Praat (desktop) | Gold-standard acoustic analysis | Research use |
| VoiceSauce | Multi-parameter extraction | Research use |
Baseline evaluation
Quantitative output
Interpretation
Machine Learning Speech Analysis Distinguishes CBD from PSP/PD. Mov Disord. 2025. 2025. ↩︎ ↩︎ ↩︎
Harmon M, et al. Formant Analysis in Corticobasal Syndrome. Journal of Speech, Language, and Hearing Research. 2024. ↩︎
Johansson K, et al. Jitter and Shimmer as Biomarkers in Parkinsonian Syndromes. Sensors. 2023. ↩︎
Rusz J, et al. Acoustic Analysis in Atypical Parkinsonism Differential Diagnosis. Journal of Neurology. 2023. ↩︎ ↩︎
Tsanas A, et al. Quantitative Speech Metrics in Progressive Supranuclear Palsy. Movement Disorders. 2024. ↩︎
Robinzon H, et al. Smartphone-Based Voice Analysis in Movement Disorders. NPJ Digital Medicine. 2023. ↩︎