Audio-Visual Speech Enhancement Using Conditional Variational Auto-Encoders

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 gen...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE/ACM transactions on audio, speech, and language processing Jg. 28; S. 1788 - 1800
Hauptverfasser: Sadeghi, Mostafa, Leglaive, Simon, Alameda-Pineda, Xavier, Girin, Laurent, Horaud, Radu
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 01.01.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Institute of Electrical and Electronics Engineers
Schlagworte:
Algorithms
Audio data
Audio equipment
Audio-visual speech enhancement
Coders
Computer architecture
Computer Science
Computer simulation
Computer Vision and Pattern Recognition
deep generative models
Lips
Machine Learning
Monte Carlo expectation-maximization
Noise measurement
nonnegative matrix factorization
Signal and Image Processing
Sound
Speech
Speech enhancement
Speech processing
Training
variational auto-encoders
Visual signals
Visualization
Training
Speech enhancement
Visualization
Lips
Noise measurement
Computer architecture
ISSN:2329-9290, 2329-9304
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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 article, 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 proposed audio-visual CVAE effectively fuses audio and visual information, and it improves the speech enhancement performance compared with the audio-only VAE model, especially when the speech signal is highly corrupted by noise. We also show that the proposed unsupervised audio-visual speech enhancement approach outperforms a state-of-the-art supervised deep learning method.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2329-9290
2329-9304
DOI:10.1109/TASLP.2020.3000593