Open AccessLinear transformation on x‐vector for text‐independent speaker verification
Author(s) -
Xu Longting,
Ren Bo,
Zhang Guanglin,
Yang Jichen
Publication year - 2019
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
ISSN - 1350-911X
DOI - 10.1049/el.2019.1264
Subject(s) - speaker verification , transformation (genetics) , vector (molecular biology) , artificial neural network , nist , algorithm , computer science , support vector machine , embedding , mathematics , pattern recognition (psychology) , speech recognition , artificial intelligence , speaker recognition , biochemistry , chemistry , gene , recombinant dna
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.