Disentanglement Learning for Variational Autoencoders Applied to Audio-Visual Speech Enhancement

Abstract

Recently, the standard variational autoencoder has been successfully used to learn a probabilistic prior over speech signals, which is then used to perform speech enhancement. Variational autoencoders have then been conditioned on a label describing a high-level speech attribute (e.g. speech activity) that allows for a more explicit control of speech generation. However, the label is not guaranteed to be disentangled from the other latent variables, which results in limited performance improvements compared to the standard variational autoencoder. In this work, we propose to use an adversarial training scheme for variational autoencoders to disentangle the label from the other latent variables. At training, we use a discriminator that competes with the encoder of the variational autoencoder. Simultaneously, we also use an additional encoder that estimates the label for the decoder of the variational autoencoder, which proves to be crucial to learn disentanglement. We show the benefit of the proposed disentanglement learning when a voice activity label, estimated from visual data, is used for speech enhancement.

arXiv commentarXiv admin note: text overlap with arXiv:2102.06454

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• An Introduction to Variational Autoencoders
• Semi-Supervised Learning with Deep Generative Models
• Disentangling by Factorising
• Fader Networks: Manipulating Images by Sliding Attributes
• Learning Disentangled Representations with Semi-Supervised Deep Generative Models
• Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization
• Variational Autoencoder for Speech Enhancement with a Noise-Aware Encoder
• A variance modeling framework based on variational autoencoders for speech enhancement
• Disentangling Factors of Variation Using Few Labels
• Adversarial Information Factorization
• Guided Variational Autoencoder for Speech Enhancement With a Supervised Classifier

Cited by in corpus (3)

• Speech Enhancement and Dereverberation with Diffusion-based Generative Models
• Integrating Uncertainty into Neural Network-based Speech Enhancement
• Towards model-free stellar chemical abundances. Potential applications in the search for chemically peculiar stars in large spectroscopic surveys