# MelGlow: Efficient Waveform Generative Network Based on Location-Variable Convolution

arXiv: https://arxiv.org/abs/2012.01684 · HTML: https://mlsanity.com/paper/2012.01684/

## Key facts

- Cited by 3 papers in the map (data through 13 Oct 2026).
- First posted on arXiv 3 Dec 2020.

## Built on by (most cited first, 3 of 3)

- [cMelGAN: An Efficient Conditional Generative Model Based on Mel Spectrograms](https://mlsanity.com/paper/2205.07319/) (2022)
- [Improve GAN-based Neural Vocoder using Pointwise Relativistic LeastSquare GAN](https://mlsanity.com/paper/2103.14245/) (2021)
- [WOLONet: Wave Outlooker for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2206.09920/) (2022)

## Abstract (arXiv)

Recent neural vocoders usually use a WaveNet-like network to capture the long-term dependencies of the waveform, but a large number of parameters are required to obtain good modeling capabilities. In this paper, an efficient network, named location-variable convolution, is proposed to model the dependencies of waveforms. Different from the use of unified convolution kernels in WaveNet to capture the dependencies of arbitrary waveforms, location-variable convolutions utilizes a kernel predictor to generate multiple sets of convolution kernels based on the mel-spectrum, where each set of convolution kernels is used to perform convolution operations on the associated waveform intervals. Combining WaveGlow and location-variable convolutions, an efficient vocoder, named MelGlow, is designed. Experiments on the LJSpeech dataset show that MelGlow achieves better performance than WaveGlow at small model sizes, which verifies the effectiveness and potential optimization space of location-variable convolutions.