Work

Voice vocoder speed vs quality: HiFi-GAN vs BigVGAN, 48 kHz for +0.2 MOS

Year: 2026

Type: preprint

Abstract: HiFi-GAN vs BigVGAN: isolating activation and anti-aliasing yields +0.2 MOS at 48 kHz, but only when mel inputs, hardware, and batch size match. Independent technical note mirroring the canonical version: https://clonemyvoice.io/blog/voice-vocoder-speed-vs-quality-hifi-gan-vs-bigvgan-48-khz-for-02-mos.php

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.24101573

Author: Cooper, Dylan

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7225735995

Cites:

Cited by:

Related to: