Piecewise Linear Definition of Transformation Functions for Speaker De-Identification

TitlePiecewise Linear Definition of Transformation Functions for Speaker De-Identification
Publication TypeConference Proceedings
Year of Publication2016
AuthorsMagariños, C, López Otero, P, Docío Fernández, L, Erro, D, Rodríguez Banga, E, García-Mateo, C
Conference NameFirst International Workshop on Sensing, Processing and Learning for Intelligent Machines (SPLINE)
Date Published07/2016
AbstractThe main drawback of speaker de-identification approaches using voice conversion techniques is the need for parallel corpora to train transformation functions between the source and target speakers. In this paper, a voice conversion approach that does not require training any parameters is proposed: it consists in manually defining frequency warping (FW) based transformations by using piecewise linear approximations. An analysis of the de-identification capabilities of the proposed approach using FW only or combined with F0 modification and spectral amplitude scaling (AS) was performed. Experimental results show that, using the manually defined transformations using only FW, it is not possible to obtain de-identified natural sounding speech. Nevertheless, when modifying the F0, both de-identification accuracy and naturalness increase to a great extent. A slight improvement in de-identification was also obtained when applying spectral amplitude scaling.
Citation Key591