Przemyslaw Maziewski

Reduction of parasitic pitch variations in archival musical recordings

A new method for reducing parasitic pitch variations in archival audio recordings is presented. The method is intended for analyzing movie soundtracks recorded in optical films. It utilizes image processing for calculating and reducing effects of tape shrinkage being one of the main reasons for parasitic pitch variations in audio accompanying moving images. As long as the film tape characteristics are known the new method can be easily tuned to analyze archival recordings. The new method is also compared to some previous approaches to pitch variation correction.

An intuitive graphical user interface for the Parkinson's Disease patients

In this paper a discussion on the design and development of the graphical user interface (GUI) dedicated to Parkinsons Disease (PD) patients is presented. The interface is intended for a group of PD patients with less severe motor symptoms, who are living at their home independently or with help of a caregiver. The GUI is designed to enable an interaction for the non-computer literate PD patients with a computer-based system. The system will allow for objectively recording the patient diaries, self assessments, taken medication confirmations and other features important for the diagnosis. This will enable physicians to prepare more accurate evaluation and better diagnostic decisions.

Intelligent algorithms for optical track audio restoration

The Unpredictability Measure computation algorithm applied to psychoacoustic model-based broadband noise attenuation is discussed. A learning decision algorithm based on a neural network is employed for determining audio signal useful components acting as maskers of the spectral components classified as noise. An iterative algorithm for calculating the sound masking pattern is presented. The routines for precise extraction of sinusoidal components from sound spectrum were examined, such as estimation of pitch variations in the optical track audio affected by parasitic frequency modulation. The results obtained employing proposed intelligent signal processing algorithms will be presented and discussed in the paper.

Some Techniques for Wow Effect Reduction

Wow distortion reduction has not attracted an adequate scientific attention so far. Only few papers on the subject are available, concerning mostly archive gramophone records, wax cylinders, and magnetic tapes affected by wow. This paper outlines researched wow reduction algorithms concerning archive movie soundtracks, or more generally audio recordings accompanying archival visual contents. The methods presented here are based on the pilot tone tracking, on the spectral analysis of genuine audio components, and on non-uniform resampling. The paper provides only a short overview of the concepts founding those methods; other studied approaches to the wow processing, as well as a more detailed description of the presented ones, can be found in referenced papers.

Intelligent algorithms for movie sound tracks restoration

Two algorithms for movie sound tracks restoration are discussed in the paper. The first algorithm is the unpredictability measure computation applied to the psychoacoustic model-based broadband noise attenuation. A learning decision algorithm, based on a neural network, is employed for determining useful audio signal components acting as maskers of the noisy spectral parts. An application of the rough set decision system to this task is also considered. An iterative method for calculating the sound masking pattern is presented. The second of presented algorithms is the routine for precise evaluation of parasite frequency modulations (wow) utilizing sinusoidal components extracted from the sound spectrum. The results obtained employing proposed intelligent signal processing algorithms, as well as the relationship between both routines, will be presented and discussed in the paper.

Computational intelligence approach to archival musical recordings

An algorithmic approach to wow defect estimation in archival musical recordings is presented. The wow estimation is based on the simultaneous analysis of many sinusoidal components, which are assumed to depict the defect. The rough determination of sinusoidal components in analyzed musical recording is performed by standard sinusoidal modeling procedures employing magnitude and phase spectra analysis. Since archival recordings tend to contain distorted tonal structure, the basic sinusoidal modeling approach is often found insufficient, resulting in audible distortions in the restored signal. It is found that the standard sinusoidal modeling approach is prone to errors, especially when strong frequency or amplitude variations of sinusoidal components occur. It may result in gaps or inappropriately matched components, leading to incorrect estimation of the wow distortion. Hence, some refinements to sinusoidal component analysis including interpolation and extrapolation of tonal components are proposed. As i...