Yuying Xie, Thomas Arildsen, Zheng-Hua Tan. Disentangled Speech Representation Learning Based on Factorized Hierarchical Variational Autoencoder with Self-Supervised Objective. In 31st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2021, Gold Coast, Australia, October 25-28, 2021. pages 1-6, IEEE, 2021. [doi]
Abstract is missing.