Log In Sign Up

AMFFCN: Attentional Multi-layer Feature Fusion Convolution Network for Audio-visual Speech Enhancement

by   Xinmeng Xu, et al.

Audio-visual speech enhancement system is regarded to be one of promising solutions for isolating and enhancing speech of desired speaker. Conventional methods focus on predicting clean speech spectrum via a naive convolution neural network based encoder-decoder architecture, and these methods a) not adequate to use data fully and effectively, b) cannot process features selectively. The proposed model addresses these drawbacks, by a) applying a model that fuses audio and visual features layer by layer in encoding phase, and that feeds fused audio-visual features to each corresponding decoder layer, and more importantly, b) introducing soft threshold attention into the model to select the informative modality softly. This paper proposes attentional audio-visual multi-layer feature fusion model, in which soft threshold attention unit are applied on feature mapping at every layer of decoder. The proposed model demonstrates the superior performance of the network against the state-of-the-art models.


Improving Visual Speech Enhancement Network by Learning Audio-visual Affinity with Multi-head Attention

Audio-visual speech enhancement system is regarded as one of promising s...

MFFCN: Multi-layer Feature Fusion Convolution Network for Audio-visual Speech Enhancement

The purpose of speech enhancement is to extract target speech signal fro...

Audio-Visual Wake Word Spotting System For MISP Challenge 2021

This paper presents the details of our system designed for the Task 1 of...

Audio-Visual Speech Enhancement based on Multimodal Deep Convolutional Neural Networks

Speech enhancement (SE) aims to reduce noise in speech signals. Most SE ...

Channel-Attention Dense U-Net for Multichannel Speech Enhancement

Supervised deep learning has gained significant attention for speech enh...

Dynamic Kernels and Channel Attention with Multi-Layer Embedding Aggregation for Speaker Verification

State-of-the-art speaker verification frameworks have typically focused ...