Guided Variational Autoencoder for Speech Enhancement With a Supervised Classifier

Abstract

Recently, variational autoencoders have been successfully used to learn a probabilistic prior over speech signals, which is then used to perform speech enhancement. However, variational autoencoders are trained on clean speech only, which results in a limited ability of extracting the speech signal from noisy speech compared to supervised approaches. In this paper, we propose to guide the variational autoencoder with a supervised classifier separately trained on noisy speech. The estimated label is a high-level categorical variable describing the speech signal (e.g. speech activity) allowing for a more informed latent distribution compared to the standard variational autoencoder. We evaluate our method with different types of labels on real recordings of different noisy environments. Provided that the label better informs the latent distribution and that the classifier achieves good performance, the proposed approach outperforms the standard variational autoencoder and a conventional neural network-based supervised approach.

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• An Introduction to Variational Autoencoders
• Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
• Semi-Supervised Learning with Deep Generative Models
• Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation
• Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization

Cited by in corpus (5)

• Speech Enhancement and Dereverberation with Diffusion-based Generative Models
• Disentanglement Learning for Variational Autoencoders Applied to Audio-Visual Speech Enhancement
• Learning and controlling the source-filter representation of speech with a variational autoencoder
• Integrating Statistical Uncertainty into Neural Network-Based Speech Enhancement
• Integrating Uncertainty into Neural Network-based Speech Enhancement