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
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.