Linear transformation on x‐vector for text‐independent speaker verification. Issue 15 (1st July 2019)

• Record Type: Journal Article
• Authors: Xu, Longting; Ren, Bo; Zhang, Guanglin; Yang, Jichen
• Is Part Of: Electronics letters. Volume 55:Issue 15(2019)
• Page Start: 864
• Page End: 866
• Publication Date: 2019-07-01
• Subjects: speaker recognition -- vectors -- neural nets; text‐independent speaker verification -- parallel factor analysis -- linear transformation expression -- background i‐vectors -- $‐vector model -- x‐vector models -- total variability model -- deep neural network -- speaker variability -- NIST 2010 dataset -- equal error rate; Electronics -- Periodicals; 621.381
• DOI: 10.1049/el.2019.1264
• Languages: English
• ISSNs: 0013-5194

Abstract

Abstract : Total variability model‐based i‐vector and deep neural network‐based embedding x‐vector are both widely used for text‐independent speaker verification. In this Letter, a novel model is proposed, which can contain information of both i‐vector and x‐vector by using parallel factor analysis. The authors aim to obtain a linear transformation expression for x‐vectors based on background i‐vectors and x‐vectors, and consider the linearly transformed x‐vector as the novel model, thus they name it as x l ‐vector. The novel x l ‐vector can maximise intra and minimise inner speaker variability, in addition, it can improve the system performance without latency. Experiments were conducted on NIST 2010 dataset, and in terms of equal error rate, they observe up to 37.27 and 53.38% relative improvement of the authors proposed x l ‐vector model compared to the i‐vector and x‐vector models, respectively.