Audio-Visual Speech Enhancement Using Multimodal Deep Convolutional Neural Networks

By Jen-Cheng Hou, Syu-Siang Wang, Ying-Hui Lai, Yu Tsao, Hsiu-Wen Chang, Hsin-Min Wang. 2017

225 citations recorded by the source corpus.

Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this paper, inspired by multimodal learning, which utilizes data from different modalities, and the recent success of convolutional neural networks (CNNs) in SE, we propose an audio–visual deep CNNs (AVDCNN) SE model, which incorporates audio and visual streams into a unified network model. We also propose a multitask learning framework for reconstructing audio and visual signals at the output layer. Precisely speaking, the proposed AVDCNN model is structured as an audio–visual encoder–decoder network, in which audio and visual data are first processed using individual CNNs, and then fused into a joint network to generate enhanced speech (the primary task) and reconstructed images (the secondary task) at the output layer. The model is trained in an end-to-end manner, and parameters are jointly learned through back propagation. We evaluate enhanced speech using five instrumental criteria. Results show that the AVDCNN model yields a notably superior performance compared with an audio-only CNN-based SE model and two conventional SE approaches, confirming the effectiveness of integrating visual information into the SE process. In addition, the AVDCNN model also outperforms an existing audio–visual SE model, confirming its capability of effectively combining audio and visual information in SE.

Subfields: Cognitive Neuroscience, Computational Mechanics, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computational Mechanics

In Signal Processing

Citations in the corpus

SEANet: A Multi-modal Speech Enhancement Network (2020, neutral): “For example, the work in [18] uses tight crops of mouth images to denoise speech.”
Audio-Visual Scene Analysis with Self-Supervised Multisensory Features (2018, methodology): “Our formulation of the problem resembles recent audio-visual and audio-only separation work [34,36,67,42].”
A Survey on Deep Learning for Multimodal Data Fusion (2020, background): “For instance, Hou, Wang, Lai, Chang, and Wang (2018) proposed a multimodal speech enhancement framework.”
NAUTILUS: A Versatile Voice Cloning System (2020, methodology): “Our proposed system is a multimodal neural network [5], [6], that can be used as TTS [22] or VC [23].”
MMTM: Multimodal Transfer Module for CNN Fusion (2019, background): “Stateof-the-art results have been achieved by recent AVSE models that use deep neural networks [6, 7, 33, 34].”
The Conversation: Deep Audio-Visual Speech Enhancement (2018, methodology): “[28] also use a similar audio-visual fusion method, trained to both generate the clean signal and to reconstruct the video.”
SpeechPainter: Text-conditioned Speech Inpainting (2022, background): “Also relevant, but not directly related to our work, are methods that enhance speech based on modalities other than text: using facial crops of the target speaker, denoising [6], inpainting speech [15] or separating a target speaker from a mixture [4, 20], and enhancing speech based on accelerometer”
VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency (2021, methodology): “We first evaluate on audio-visual speech separation and compare to a series of state-of-the-art methods [19, 2, 4, 15, 21, 60, 12, 35] and multiple baselines:”
An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation (2020, methodology): “SIG / BAK / OVRL [118] 2003 Extension of MOS considering signal [99] distorsion and noise intrusiveness”