Neural adversarial learning for speaker recognition

檔案

本條目沒有附加檔案。

至出版者網站查看(DOI) ›

日期

2019-11-01

類型

期刊名稱

COMPUTER SPEECH AND LANGUAGE

卷期與頁次

第 58 卷,頁 422–440

ISSN

0885-2308

語言

英文

摘要

This paper presents the adversarial learning approaches to deal with various tasks in speaker recognition based on probabilistic discriminant analysis (PLDA) which is seen as a latent variable model for reconstruction of i-vectors. The first task aims to reduce the dimension of i-vectors based on an adversarial manifold learning where the adversarial neural networks of generator and discriminator are merged to preserve neighbor embedding of i-vectors in a low-dimensional space. The generator is trained to fool the discriminator with the generated samples in latent space. A PLDA subspace model is constructed by jointly minimizing a PLDA reconstruction error, a manifold loss for neighbor embedding and an adversarial loss caused by the generator and discriminator. The second task of adversarial learning is developed to tackle the imbalanced data problem. A PLDA based generative adversarial network is trained to generate new i-vectors to balance the size of training utterances across different speakers. An adversarial augmentation learning is proposed for robust speaker recognition. In particular, the minimax optimization is performed to estimate a generator and a discriminator where the class conditional i-vectors produced by generator could not be distinguished from real i-vectors via discriminator. A multiobjective learning is realized for a specialized neural model with the cosine similarity between real and fake i-vectors as well as the regularization for Gaussianity. Experiments are conducted to show the merit of adversarial learning in subspace construction and data augmentation for PLDA-based speaker recognition. (C) 2019 Elsevier Ltd. All rights reserved.

所屬典藏

期刊論文
顯示完整詮釋資料 統計資料

引用此條目

Chien, J.-T., & Peng, K.-T. (2019). Neural adversarial learning for speaker recognition. COMPUTER SPEECH AND LANGUAGE, 58, 422–440. https://doi.org/10.1016/j.csl.2019.06.003

BibTeX RIS

引用文字依 APA 第 7 版格式自動產生,使用前請再核對。

分享

永久網址:https://ir.lib.nycu.edu.tw/handle/11536/152673