No abstract

Voice assessment requires simple and painless exams. Modern technologies provide the necessary resources for voice signal processing. Techniques based on nonlinear dynamics seem to asses the complexity of voice more accurately than other methods. Vocal dynamic visual pattern (VDVP) is based on nonlinear methods and provides qualitative and quantitative information. Here we characterize healthy and Reinke´s edema voices by means of perturbation measures and VDVP analysis. VDPD and jitter show different results for both groups, while amplitude perturbation has no difference. We suggest that VDPD analysis improve and complement the evaluation methods available for clinicians.

No abstract

This work proposes a modular approach, using signal processing techniques and artificial neural networks for diagnosing of glottal conditions related to laryngeal pathologies. While signal processing tcchniques are used to cxtract acoustic features from the human voice, artificial neural networks usc these features to perform the diagnosis. These features wcre based on abnormal movement of vocal folds and incomplete closure of glottis. Simple statistical methods, like robust estimators. Mann-Whitney test and Principal Cmnponent Analysis were uscd to improvc the percentage of correct classiiication, >illowing up to 82.228 of identification of the glottal conditions using only voice analysis.

No abstract

No abstract

No abstract