End-to-End Speech Enhancement Using Fully Convolutional Networks with Skip Connections

Land cover Classified maps obtained from deep learning methods such as Convolutional neural networks (CNNs) and fully convolutional networks (FCNs) usually have high classification accuracy but with the detailed structures of objects lost or smoothed. In this work, we develop a methodology based on fully convolutional networks (FCN) that is trained in an end-to-end fashion using aerial RGB images only as input. Skip connections are introduced into the FCN architecture to recover high spatial details from the lower convolutional layers. The experiments are conducted on the city of Goma in the Democratic Republic of Congo. We compare the results to a state-of-the art approach based on a semi-automatic Geographic object image-based analysis (GEOBIA) processing chain. State-of-the art classification accuracies are obtained by both methods whereby FCN and the best baseline method have an overall accuracy of 91.3% and 89.5% respectively. The maps have good visual quality and the use of an FCN skip architecture minimizes the rounded edges that is characteristic of FCN maps. Additional experiments are done to refine FCN classified maps using segments obtained from GEOBIA generated at different scale and minimum segment size. High OA of up to 91.5% is achieved accompanied with an improved edge delineation in the FCN maps, and future work will involve explicitly incorporating boundary information from the GEOBIA segmentation into the FCN pipeline in an end-to-end fashion. Finally, we observe that FCN has a lower computational cost than the standard patch-based CNN approach especially at inference.

Download Full-text

Multichannel Speech Enhancement by Raw Waveform-Mapping Using Fully Convolutional Networks

IEEE/ACM Transactions on Audio Speech and Language Processing ◽

10.1109/taslp.2020.2976193 ◽

2020 ◽

Vol 28 ◽

pp. 1888-1900 ◽

Cited By ~ 1

Author(s):

Chang-Le Liu ◽

Sze-Wei Fu ◽

You-Jin Li ◽

Jen-Wei Huang ◽

Hsin-Min Wang ◽

...

Keyword(s):

Speech Enhancement ◽

Convolutional Networks ◽

Fully Convolutional Networks

Download Full-text

End-to-End Denoising of Dark Burst Images using Recurrent Fully Convolutional Networks

Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications ◽

10.5220/0008895901890196 ◽

2020 ◽

Author(s):

Lan Ma ◽

Di Zhao ◽

Songnan Li ◽

Dahai Yu

Keyword(s):

Convolutional Networks ◽

Fully Convolutional Networks ◽

End To End

Download Full-text

Deep Attention Gated Dilated Temporal Convolutional Networks with Intra-Parallel Convolutional Modules for End-to-End Monaural Speech Separation

10.21437/interspeech.2019-1373 ◽

2019 ◽

Cited By ~ 8

Author(s):

Ziqiang Shi ◽

Huibin Lin ◽

Liu Liu ◽

Rujie Liu ◽

Jiqing Han ◽

...

Keyword(s):

Speech Separation ◽

Convolutional Networks ◽

End To End

Download Full-text

A data augmentation approach to train fully convolutional networks for left ventricle segmentation

Magnetic Resonance Imaging ◽

10.1016/j.mri.2019.08.004 ◽

2020 ◽

Vol 66 ◽

pp. 152-164

Author(s):

Adan Lin ◽

Junhao Wu ◽

Xuan Yang

Keyword(s):

Left Ventricle ◽

Data Augmentation ◽

Convolutional Networks ◽

Fully Convolutional Networks ◽

Ventricle Segmentation

Download Full-text

Efficient End-to-End Sentence-Level Lipreading with Temporal Convolutional Networks

Applied Sciences ◽

10.3390/app11156975 ◽

2021 ◽

Vol 11 (15) ◽

pp. 6975

Author(s):

Tao Zhang ◽

Lun He ◽

Xudong Li ◽

Guoqing Feng

Keyword(s):

Performance Improvement ◽

State Of The Art ◽

Error Rates ◽

Convolutional Network ◽

Convolutional Networks ◽

Sentence Level ◽

End To End ◽

High Level ◽

Improved Accuracy ◽

Talking Face

Lipreading aims to recognize sentences being spoken by a talking face. In recent years, the lipreading method has achieved a high level of accuracy on large datasets and made breakthrough progress. However, lipreading is still far from being solved, and existing methods tend to have high error rates on the wild data and have the defects of disappearing training gradient and slow convergence. To overcome these problems, we proposed an efficient end-to-end sentence-level lipreading model, using an encoder based on a 3D convolutional network, ResNet50, Temporal Convolutional Network (TCN), and a CTC objective function as the decoder. More importantly, the proposed architecture incorporates TCN as a feature learner to decode feature. It can partly eliminate the defects of RNN (LSTM, GRU) gradient disappearance and insufficient performance, and this yields notable performance improvement as well as faster convergence. Experiments show that the training and convergence speed are 50% faster than the state-of-the-art method, and improved accuracy by 2.4% on the GRID dataset.

Download Full-text