Papers › VocBench: A Neural Vocoder Benchmark for Speech Synthesis

VocBench: A Neural Vocoder Benchmark for Speech Synthesis

6 Dec 2021arXiv:2112.03099archive 2025-07-28

Ehab A. AlBadawy, Andrew Gibiansky, Qing He, JiLong Wu, Ming-Ching Chang, Siwei Lyu

Neural vocoders, used for converting the spectral representations of an audio signal to the waveforms, are a commonly used component in speech synthesis pipelines. It focuses on synthesizing waveforms from low-dimensional representation, such as Mel-Spectrograms. In recent years, different approaches have been introduced to develop such vocoders. However, it becomes more challenging to assess these new vocoders and compare their performance to previous ones. To address this problem, we present VocBench, a framework that benchmark the performance of state-of-the art neural vocoders. VocBench uses a systematic study to evaluate different neural vocoders in a shared environment that enables a fair comparison between them. In our experiments, we use the same setup for datasets, training pipeline, and evaluation metrics for all neural vocoders. We perform a subjective and objective evaluation to compare the performance of each vocoder along a different axis. Our results demonstrate that the framework is capable of showing the competitive efficacy and the quality of the synthesized samples for each vocoder. VocBench framework is available at https://github.com/facebookresearch/vocoder-benchmark.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

facebookresearch/vocoder-benchmark officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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.

Tasks

Speech Synthesis

Datasets

Introduced by this paper, per the archive.

VocBench

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingConvolutionDilated Causal ConvolutionDilated ConvolutionFiLM ModuleGAN Feature MatchingGAN Hinge LossGrouped ConvolutionMelGANMelGAN Residual BlockMixture of Logistic DistributionsReLUResidual ConnectionSigmoid ActivationSoftmaxTanh ActivationWaveGradWaveGrad DBlockWaveGrad UBlockWaveNetWaveRNNWeight NormalizationWindow-based Discriminator

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