標題: BAYESIAN ADVERSARIAL LEARNING FOR SPEAKER RECOGNITION
作者: Chien, Jen-Tzung
Kuo, Chun-Lin
電機工程學系
Department of Electrical and Computer Engineering
關鍵字: generative adversarial networks;Bayesian learning;variational autoencoder;speaker recognition
公開日期: 1-Jan-2019
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.
URI: http://hdl.handle.net/11536/154481
ISBN: 978-1-7281-0306-8
期刊: 2019 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU 2019)
起始頁: 381
結束頁: 388
Appears in Collections:Conferences Paper