The main aim of this paper is to describe a new software program for esophageal speech treatment developed at the University of Deusto. The software tool, named “ESOIMPROVE”, allows both to characterize and to modify this speech, and provides the necessary framework to achieve a high quality and intelligible transformed esophageal speech by applying a complete range of sound effects and algorithms. In this field, this tool represents a considerable advance in the study of these voices. The final objective of the project is to obtain an esophageal speech with acceptable levels of quality and intelligibility, and some more works in this direction are being actually developed.

Download

In this paper it is described a new algorithm for esophageal speech regeneration, based on pitch and jitter modification. Traditional phase vocoder and resampling pitch scaling techniques have been used to develop a new adaptive method which scales the low esophageal speech pitch and applies a variable scaling factor significantly reducing its jitter. This method has shown to considerably improve esophageal speech quality, reducing its hoarseness and increasing its intelligibility. The presented algorithm pretends to be an important step forward in the regeneration of esophageal speech.

Download