摘要
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 latent discriminative representation learning method for speaker recognition.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 linear mapping matrix 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.
基金
Project supported by the National Natural Science Foundation of China(Nos.U1836220 and 61672267)
the Qing Lan Talent Program of Jiangsu Province,China
the Jiangsu Province Key Research and Development Plan(Industry Foresight and Key Core Technology)(No.BE2020036)。