BAYESIAN ADVERSARIAL LEARNING FOR SPEAKER RECOGNITION

檔案

本條目沒有附加檔案。

日期

2019-01-01

期刊名稱

2019 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU 2019)

卷期與頁次

頁 381–388

ISBN

978-1-7281-0306-8

語言

英文

摘要

This paper presents a new generative adversarial network (GAN) which artificially generates the i-vectors to compensate the imbalanced or insufficient data in speaker recognition based on the probabilistic linear discriminant analysis. Theoretically, GAN is powerful to generate the artificial data which are misclassified as the real data. However, GAN suffers from the mode collapse problem in two-player optimization over generator and discriminator. This study deals with this challenge by improving the model regularization through characterizing the weight uncertainty in GAN. A new Bayesian GAN is implemented to learn a regularized model from diverse data where the strong modes are flattened via the marginalization. In particular, we present a variational GAN (VGAN) where the encoder, generator and discriminator are jointly estimated according to the variational inference. The computation cost is significantly reduced. To assure the preservation of gradient values, the learning objective based on Wasserstein distance is further introduced. The issues of model collapse and gradient vanishing are alleviated. Experiments on NIST i-vector Speaker Recognition Challenge demonstrate the superiority of the proposed VGAN to the variational autoencoder, the standard GAN and the Bayesian GAN based on the sampling method. The learning efficiency and generation performance are evaluated.

所屬典藏

會議論文
顯示完整詮釋資料 統計資料

引用此條目

Chien, J.-T., & Kuo, C.-L. (2019). BAYESIAN ADVERSARIAL LEARNING FOR SPEAKER RECOGNITION. 2019 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU 2019), 381–388. https://ir.lib.nycu.edu.tw/handle/11536/154481

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/11536/154481