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

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

3 Dec 2020arXiv:2012.01684archive 2025-07-28

Zhen Zeng, Jianzong Wang, Ning Cheng, Jing Xiao

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.

PaperPDFCode

Code

JackZiLong/LVCNet mentioned on GitHubpytorch report
ZENGZHEN-TTS/LVCNet mentioned on GitHubpytorch report
zceng/lvcnet mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Affine CouplingConvolutionDilated Causal ConvolutionInvertible 1x1 ConvolutionMixture of Logistic DistributionsNormalizing FlowsWaveGlowWaveNet

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections