Enhancing voice quality in vocal tract rehabilitation device

Abstract

The assistive devices used for vocal rehabilitation by patients after Laryngectomy produce a distinctly robotic sounding speech. This study aims at introducing human-like qualities into the synthetically generated voices. A simplified source filter model, LPC coefficients and line spectral frequencies were used to characterize the vocal tract and manipulate the acoustic properties of speech. Two different mapping functions were employed: A Gaussian mixture model (GMM) and a linear regression model (LR). Objective and subjective testing showed that both mapping functions produced significant changes in the re-synthesised speech, with the LR mapping producing slightly better results. However, the subjective listening tests indicated that re- synthesized voices improved on the synthetic voice but still lacked human quality. This may imply that the vocal tract model contains only partial information pertaining to the subjective perception of artificiality in speech. Future work is aimed at investigating an elaborate model containing the speech production excitation and radiation signals.