Deep Speaker Feature Learning for Text-independent Speaker Verification
Abstract
Recently deep neural networks (DNNs) have been used to learn speaker features. However, the quality of the learned features is not sufficiently good, so a complex back-end model, either neural or probabilistic, has to be used to address the residual uncertainty when applied to speaker verification, just as with raw features. This paper presents a convolutional time-delay deep neural network structure (CT-DNN) for speaker feature learning. Our experimental results on the Fisher database demonstrated that this CT-DNN can produce high-quality speaker features: even with a single feature (0.3 seconds including the context), the EER can be as low as 7.68%. This effectively confirmed that the speaker trait is largely a deterministic short-time property rather than a long-time distributional pattern, and therefore can be extracted from just dozens of frames.
Cite
@article{arxiv.1705.03670,
title = {Deep Speaker Feature Learning for Text-independent Speaker Verification},
author = {Lantian Li and Yixiang Chen and Ying Shi and Zhiyuan Tang and Dong Wang},
journal= {arXiv preprint arXiv:1705.03670},
year = {2017}
}
Comments
deep neural networks, speaker verification, speaker feature