Audio-visual Speech Enhancement Using Conditional Variational Auto-encoders
2019 · Mostafa Sadeghi, Simon Leglaive, Xavier Alameda-Pineda, et al.
Abstract
Variational auto-encoders (VAEs) are deep generative latent variable models that can be used for learning the distribution of complex data. VAEs have been successfully used to learn a probabilistic prior over speech signals, which is then used to perform speech enhancement. One advantage of this generative approach is that it does not require pairs of clean and noisy speech signals at training. In this paper, we propose audio-visual variants of VAEs for single-channel and speaker-independent speech enhancement. We develop a conditional VAE (CVAE) where the audio speech generative process is conditioned on visual information of the lip region. At test time, the audio-visual speech generative model is combined with a noise model based on nonnegative matrix factorization, and speech enhancement relies on a Monte Carlo expectation-maximization algorithm. Experiments are conducted with the recently published NTCD-TIMIT dataset as well as the GRID corpus. The results confirm that the propose
Authors
(none)
Tags
Stats
Related papers
- Robust Unsupervised Audio-visual Speech Enhancement Using A Mixture Of Variational Autoencoders (2019)9.23
- Mixture Of Inference Networks For Vae-based Audio-visual Speech Enhancement (2019)10.35
- Switching Variational Auto-encoders For Noise-agnostic Audio-visual Speech Enhancement (2021)7.16
- Audio-visual Speech Enhancement With A Deep Kalman Filter Generative Model (2022)6.34
- Deep Variational Generative Models For Audio-visual Speech Separation (2020)0.00
- A Statistically Principled And Computationally Efficient Approach To Speech Enhancement Using Variational Autoencoders (2019)9.23
- Statistical Speech Enhancement Based On Probabilistic Integration Of Variational Autoencoder And Non-negative Matrix Factorization (2017)15.00
- Unsupervised Speech Enhancement Using Dynamical Variational Auto-encoders (2021)13.28