Automated characterization of esophageal and severely injured voices by means of acoustic parameters

In the scope of digitized speech signals with severe pathologies, as the esophageal voices are, it is impossible the objective assessment of the voice based on a set of parameters accepted by the scientific community like pitch, jitter, shimmer or HNR. This impossibility is due to healthy voices or with slight pathologies can be only evaluated with commercial applications. However, this paper presents a robust and precise algorithm that allows the automated calculation of pitch and jitter on very noisy and low quality voice signals. Therefore, both the improvement achieved due to medical treatment and the evaluation of digital signal processing algorithms will be measurable based on objective criteria.

1 Introduction

Speech signal processing plays an important role within the digital processing projects and investigations. Within this field, the esophageal voices are being objective of analysis and transformation [2], [3] but these have the limitation of measuring their quality only with subjective criteria as hearing tests. This is because an evaluation based on the calculation of objective parameters like pitch, jitter, shimmer or the harmonic to noise ratio HNR demands a high precision in the definition of the beginnings and ends of cycle in the voice signal.