Methods > General > Skip Connection Blocks

MelGAN Residual Block

Introduced by Kumar et al. in MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis

The MelGAN Residual Block is a convolutional residual block used in the MelGAN generative audio architecture. It employs residual connections with dilated convolutions. Dilations are used so that temporally far output activations of each subsequent layer has significant overlapping inputs. Receptive field of a stack of dilated convolution layers increases exponentially with the number of layers. Incorporating these into the MelGAN generator allows us to efficiently increase the induced receptive fields of each output time-step. This effectively implies larger overlap in the induced receptive field of far apart time-steps, leading to better long range correlation.

Source: MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis

Latest Papers

PAPER DATE
Improve GAN-based Neural Vocoder using Pointwise Relativistic LeastSquare GAN
Congyi WangYu ChenBin WangYi Shi
2021-03-26
Universal MelGAN: A Robust Neural Vocoder for High-Fidelity Waveform Generation in Multiple Domains
| Won JangDan LimJaesam Yoon
2020-11-19
StyleMelGAN: An Efficient High-Fidelity Adversarial Vocoder with Temporal Adaptive Normalization
| Ahmed MustafaNicola PiaGuillaume Fuchs
2020-11-03
SpeedySpeech: Efficient Neural Speech Synthesis
| Jan VainerOndřej Dušek
2020-08-09
VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Network
| Jinhyeok YangJun-Mo LeeYoungik KimHoon-Young ChoInjung Kim
2020-07-30
Adversarial representation learning for private speech generation
| David EricssonAdam ÖstbergEdvin Listo ZecJohn MartinssonOlof Mogren
2020-06-16
SE-MelGAN -- Speaker Agnostic Rapid Speech Enhancement
Luka ChkhetianiLevan Bejanidze
2020-06-13
MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
| Kundan KumarRithesh KumarThibault de BoissiereLucas GestinWei Zhen TeohJose SoteloAlexandre de BrebissonYoshua BengioAaron Courville
2019-10-08

Tasks

TASK PAPERS SHARE
Speech Synthesis 4 80.00%
Speech Enhancement 1 20.00%

Categories