Parkinson’s disease (PD) presents both motor and non-motor impairments, including alterations in spontaneous blinking behavior. Oculomotor biomarkers, often preceding major motor symptoms, offer a non-invasive and quantitative approach to characterize oculomotor impairments. In this paper, we propose an automated framework for PD classification based on spontaneous blink recording. We introduce a novel dataset comprising healthy controls, PD patients without medication, PD patients in both medication states (PD_OFF and PD_ON). We extracted blink-related features— blink rate, mean inter-blink interval (IBI), and IBI variability—to assess their discriminative power in multi-class classification. Among several standard machine learning algorithms, gradient boosting achieved the highest accuracy (84.44%), successfully distinguishing all four groups. Other models (RF, LGBM, KNN) also demonstrated robust performance. These findings indicate that blink-based metrics can reliably capture both disease presence and medication effects, supporting their potential as non-invasive biomarkers for monitoring PD progression and treatment response.

The performance of adaptive acoustic echo cancelers (AEC) is sensitive to the nonstationarity and correlation of speech signals. In this paper, we explore a new approach based on an adaptive AEC driven by data hidden in speech, to enhance the AEC robustness. We propose a two-stage AEC, where the first stage is a classical NLMS-based AEC driven by the far-end speech. In the signal, we embed-in an extended conception of data hiding-an imperceptible white and stationary signal, i.e., a watermark. The goal of the second stage AEC is to identify the misalignment of the first stage. It is driven by the watermark solely and takes advantage of its appropriate properties (stationary and white) to improve the robustness of the two-stage AEC to the nonstationarity and correlation of speech, and thus reduce the overall system misadjustment. We test two kinds of implementations: in the first implementation, referred to as adaptive watermark driven AEC (A-WdAEC), the watermark is a white stationary Gaussian noise. Driven by this signal, the second stage converges faster than the classical AEC and provides better performance in steady state. In the second implementation, referred to as maximum length sequences WdAEC (MLS-WdAEC), the watermark is built from MLS. Thus, the second stage performs a block identification of the first stage misalignment, given by the circular correlation watermark/preprocessed version of the first stage residual echo. The advantage of this implementation lies in its robustness against noise and undermodeling. Simulation results show the relevance of the “WdAEC” approach, compared to the classical “error-driven AEC.”

Many audio processing algorithms have optimal performance for specific signal statistical distributions that may not be fulfilled for all signals. When the original signal is available, we propose to add an inaudible noise so that the distribution of the signal-plus-noise mixture is as close as possible to a given target distribution. The proposed generic algorithm (independent from the application) adds iteratively a low-power white noise to a flat-spectrum version of the signal, until the target distribution or the noise audibility is reached. The latter is assessed through a frequency masking model. Two implementations of this sound reshaping are described, according to the level of the targeted transformation and to the foreseen application: histogram global reshaping (HGR) to change the global shape of the histogram and histogram local reshaping (HLR) to locally “chisel” the histogram, but keeping the global shape unchanged. These two variants are illustrated by two applications, where the inaudibility of the noise generated by the algorithm is required: “sparsification” for source separation and low-pass filtering of the histogram for application of the quantization theorem, respectively. In both cases, the target histogram is reached or almost reached, and the transformation is inaudible. The experiments show that the source separation performs better with HGR and that the HLR allows a better application of the quantization theorem.

Nonlinear audio system identification generally relies on Gaussianity, whiteness and stationarity hypothesis on the input signal, although audio signals are non-Gaussian, highly correlated and non-stationary. However, since the physical behavior of nonlinear audio systems is input-dependent, they should be identified using natural audio signals (speech or music) as input, instead of artificial signals (sweeps or noise) as usually done. We propose an identification scheme that conditions audio signals to fit the desired properties for an efficient identification. The identification system consists in (1) a Gaussianization step that makes the signal near-Gaussian under a perceptual constraint; (2) a predictor filterbank that whitens the signal; (3) an orthonormalization step that enhances the statistical properties of the input vector of the last step, under a Gaussianity hypothesis; (4) an adaptive nonlinear model. The proposed scheme enhances the convergence rate of the identification and reduces the steady state identification error, compared to other schemes, for example the classical adaptive nonlinear identification.

In this paper, we propose the concept of ldquodoping watermarkingrdquo, whose principle is to add an imperceptible noise to an host signal in order to improve its properties. Especially, our aim is to reduce the spectral support of the probability density function (PDF) of an audio signal in order to match the conditions of the quantization theorem. In this context, we develop a specific audio watermarking algorithm and test its performance on real audio signals. This watermark allows to recover the PDF of a digital signal from a sub-quantized version of the signal, with very low error.

In a telephone link, the voice timbre is impaired by spectral distortions generated by the analog parts of the link. We first evaluate from a perceptual point of view an equalization method consisting in matching the long term spectrum of the processed signal to a reference spectrum. This evaluation shows a satisfying restoration of the timbre for most speakers. For some speakers however, a noticeable spectral distortion remains. That is why we propose a multi-referenced equalizer, based on a classification of speakers and using a different reference spectrum for each class. This leads to a decrease of the spectral distortion and, as a consequence, to a significant improvement of the timbre correction. 1.

In a telephone link, the voice timbre is affected by the loss of low frequencies components and distortions due to the analog lines. We analyze first how the quantization noise limits the restoration of the timbre. Within this limitation, a method of equalization, inspired by the cepstral subtraction, is then proposed to correct the timbre and is validated by experimental results.