Exploiting Nonlinear Recurrence and Fractal Scaling Properties for Voice Disorder Detection

By Max A. Little, Patrick E. McSharry, S. Roberts, D. Costello, I. Moroz. BioMedical Engineering OnLine, 2007

894 citations recorded by the source corpus.

BackgroundVoice disorders affect patients profoundly, and acoustic tools can potentially measure voice function objectively. Disordered sustained vowels exhibit wide-ranging phenomena, from nearly periodic to highly complex, aperiodic vibrations, and increased "breathiness". Modelling and surrogate data studies have shown significant nonlinear and non-Gaussian random properties in these sounds. Nonetheless, existing tools are limited to analysing voices displaying near periodicity, and do not account for this inherent biophysical nonlinearity and non-Gaussian randomness, often using linear signal processing methods insensitive to these properties. They do not directly measure the two main biophysical symptoms of disorder: complex nonlinear aperiodicity, and turbulent, aeroacoustic, non-Gaussian randomness. Often these tools cannot be applied to more severe disordered voices, limiting their clinical usefulness.MethodsThis paper introduces two new tools to speech analysis: recurrence and fractal scaling, which overcome the range limitations of existing tools by addressing directly these two symptoms of disorder, together reproducing a "hoarseness" diagram. A simple bootstrapped classifier then uses these two features to distinguish normal from disordered voices.ResultsOn a large database of subjects with a wide variety of voice disorders, these new techniques can distinguish normal from disordered cases, using quadratic discriminant analysis, to overall correct classification performance of 91.8 ± 2.0%. The true positive classification performance is 95.4 ± 3.2%, and the true negative performance is 91.5 ± 2.3% (95% confidence). This is shown to outperform all combinations of the most popular classical tools.ConclusionGiven the very large number of arbitrary parameters and computational complexity of existing techniques, these new techniques are far simpler and yet achieve clinically useful classification performance using only a basic classification technique. They do so by exploiting the inherent nonlinearity and turbulent randomness in disordered voice signals. They are widely applicable to the whole range of disordered voice phenomena by design. These new measures could therefore be used for a variety of practical clinical purposes.

Subfields: Clinical Psychology, Physiology

View Paper: https://www.semanticscholar.org/paper/27e1dcd0d64bfc9d936e597d4f29b80c21571936

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Clinical Psychology

Resul Das

In Physiology

Citations in the corpus

Ranking and combining multiple predictors without labeled data (2013, background): “ 34 good return/bad return [6] MGT (MAGIC Gamma Telescope) 19,020 11 signal/background [7] MM (Mammographic masses) 961 6 disease severity (2 classes) [8] PD (Parkinson data) 197 23 aected/unaected [9] SD (Spambase data) 4,601 57 spam/not spam [10] WBC (Wisconsin breast cancer data) 699 10 benign/ma”
Accurate Telemonitoring of Parkinson's Disease Progression by Noninvasive Speech Tests (2009, methodology): “The recently proposed speech signal processing methods are recurrence period density entropy (RPDE), detrended fluctuation analysis (DFA), and pitch period entropy (PPE) [22], [29].”
Collection and Analysis of a Parkinson Speech Dataset With Multiple Types of Sound Recordings (2013, background): “Such systems lower the inconvenience and cost of physical visits of PD patients to the medical clinic, enable the early diagnosis of the disease, and also lessen the workload of medical personnel [7], [13]–[15].”
A comparison of multiple classification methods for diagnosis of Parkinson disease (2010, methodology): “methods are based on nonlinear dynamical systems theory (Kantz & Schreiber, 1999; Little et al., 2007).”