Disentanglement Learning for Variational Autoencoders Applied to Audio-Visual Speech Enhancement
This work addresses a specific bottleneck in audio-visual speech enhancement for applications like hearing aids or communication systems, but it is incremental as it builds on existing variational autoencoder methods.
The authors tackled the problem of limited performance improvements in variational autoencoders for speech enhancement due to entangled latent variables, and proposed an adversarial training scheme with a discriminator and an additional encoder to achieve disentanglement, resulting in improved speech enhancement when using a voice activity label estimated from visual data.
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.