Gated Residual Networks with Dilated Convolutions for Supervised Speech Separation

By Ke Tan, Jitong Chen, Deliang Wang. 2018

56 citations recorded by the source corpus.

How researchers see this paper

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

1. Deliang Wang
2. Ke Tan
3. Ashutosh Pandey
4. Kai Zhen
5. Jongmo Sung
6. Minje Kim
7. Mi Suk Lee
8. Seungkwon Beack

Citations in the corpus

• Cascaded Cross-Module Residual Learning towards Lightweight End-to-End Speech Coding (2019, methodology): “Furthermore, inspired by recent work in source separation with dilated convolutional neural network [27], we use a “bottleneck” residual learning block to further reduce the number of parameters.”
• A New Framework for CNN-Based Speech Enhancement in the Time Domain (2019, methodology): “The training and the test set for this experiment are the same as in [35], again facilitating quantitative comparisons.”
• A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement (2018, background): “A more recent study [13] developed a gated residual network (GRN) based on dilated convolutions.”