HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

Jaehyeon Kim; Jaekyoung Bae; Jungil Kong

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2010.05646 v2 pith:MKR5ZNO5 submitted 2020-10-12 cs.SD cs.LGeess.AS

Jungil Kong , Jaehyeon Kim , Jaekyoung Bae This is my paper

classification cs.SDcs.LGeess.AS

keywords speechhifi-ganqualitysynthesisaudiogenerativeadversarialautoregressive

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original abstract

Several recent work on speech synthesis have employed generative adversarial networks (GANs) to produce raw waveforms. Although such methods improve the sampling efficiency and memory usage, their sample quality has not yet reached that of autoregressive and flow-based generative models. In this work, we propose HiFi-GAN, which achieves both efficient and high-fidelity speech synthesis. As speech audio consists of sinusoidal signals with various periods, we demonstrate that modeling periodic patterns of an audio is crucial for enhancing sample quality. A subjective human evaluation (mean opinion score, MOS) of a single speaker dataset indicates that our proposed method demonstrates similarity to human quality while generating 22.05 kHz high-fidelity audio 167.9 times faster than real-time on a single V100 GPU. We further show the generality of HiFi-GAN to the mel-spectrogram inversion of unseen speakers and end-to-end speech synthesis. Finally, a small footprint version of HiFi-GAN generates samples 13.4 times faster than real-time on CPU with comparable quality to an autoregressive counterpart.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 743 citations worldwide. Full citation record

Entropy-based Coarse and Compressed Semantic Speech Representation Learning
cs.CL 2025-08 conditional novelty 6.0 of 10

Predictive entropy from a token-level speech language model finds merge boundaries, producing compressed semantic tokens that keep ASR and translation accuracy at 15 Hz while lowering latency.
MuteSwap: Visual-informed Silent Video Identity Conversion
cs.SD 2025-07 conditional novelty 6.0 of 10

A single-stage model performs zero-shot voice conversion from silent lip video and target face images, with no acoustic input at inference.
Quantize More, Lose Less: Autoregressive Generation from Residually Quantized Speech Representations
cs.SD 2025-07 reject novelty 5.0 of 10

QTTS models speech as sequences from a multi-codebook RVQ audio codec whose first codebook is trained with ASR supervision, aiming for higher-fidelity TTS than single-codebook systems.
Technical report: Impact of Duration Prediction on Speaker-specific TTS for Indian Languages
eess.AS 2025-07 conditional novelty 4.0 of 10

In a five-language zero-shot TTS study, no single duration prediction strategy dominates: speaker-prompted durations help some languages, infilling durations help others, and results vary by metric.
WaveLLDM: Design and Development of a Lightweight Latent Diffusion Model for Speech Enhancement and Restoration
cs.SD 2025-08 conditional novelty 3.0 of 10

WaveLLDM, a lightweight latent diffusion model with a neural codec, achieves low spectral distortion (LSD 0.48-0.60) on speech restoration but scores far below SOTA on PESQ and STOI.

Pith tools