Journal Home Online First Current Issue Archive For Authors Journal Information 中文版

2021, Volume 22, Issue 5

Abstract

Keywords

Related Research

Back to Top

Frontiers of Information Technology & Electronic Engineering >> 2021, Volume 22, Issue 5 doi: 10.1631/FITEE.1900690

Latent discriminative representation learning for speaker recognition

Affiliation(s): School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang 212013, China; Jiangsu Key Laboratory of Security Technology for Industrial Cyberspace, Zhenjiang 212013, China; less

Received: 2019-12-10 Accepted: 2021-05-17 Available online: 2021-05-17
HTML29 PDF 29 Collect 0

Next Previous

Abstract

Extracting discriminative speaker-specific representations from speech signals and transforming them into fixed length vectors are key steps in speaker identification and verification systems. In this study, we propose a method for . We mean that the learned representations in this study are not only discriminative but also relevant. Specifically, we introduce an additional speaker embedded lookup table to explore the relevance between different utterances from the same speaker. Moreover, a reconstruction constraint intended to learn a is introduced to make representation discriminative. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods based on the Apollo dataset used in the Fearless Steps Challenge in INTERSPEECH2019 and the TIMIT dataset.

Related Research