Papers › High Fidelity Speech Synthesis with Adversarial Networks

High Fidelity Speech Synthesis with Adversarial Networks

25 Sep 2019ICLR 2020 1arXiv:1909.11646archive 2025-07-28

Mikołaj Bińkowski, Jeff Donahue, Sander Dieleman, Aidan Clark, Erich Elsen, Norman Casagrande, Luis C. Cobo, Karen Simonyan

Generative adversarial networks have seen rapid development in recent years and have led to remarkable improvements in generative modelling of images. However, their application in the audio domain has received limited attention, and autoregressive models, such as WaveNet, remain the state of the art in generative modelling of audio signals such as human speech. To address this paucity, we introduce GAN-TTS, a Generative Adversarial Network for Text-to-Speech. Our architecture is composed of a conditional feed-forward generator producing raw speech audio, and an ensemble of discriminators which operate on random windows of different sizes. The discriminators analyse the audio both in terms of general realism, as well as how well the audio corresponds to the utterance that should be pronounced. To measure the performance of GAN-TTS, we employ both subjective human evaluation (MOS - Mean Opinion Score), as well as novel quantitative metrics (Fr\'echet DeepSpeech Distance and Kernel DeepSpeech Distance), which we find to be well correlated with MOS. We show that GAN-TTS is capable of generating high-fidelity speech with naturalness comparable to the state-of-the-art models, and unlike autoregressive models, it is highly parallelisable thanks to an efficient feed-forward generator. Listen to GAN-TTS reading this abstract at https://storage.googleapis.com/deepmind-media/research/abstract.wav.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1909.11646")

Code

Syntology Ran 2 of 5 code samples harvested from 2 repositories linked to this paper; 3 have no recorded run. Of those that ran: 2 ran · our draft was wrong.

By repository: official repository: 1 sample from 1 repository, 0 ran; community (archive-listed): 3 samples from 1 repository, 2 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

mbinkowski/DeepSpeechDistances officialmentioned on GitHubtfApache-2.0 report
izzajalandoni/tts_models mentioned on GitHubpytorchBSD-3-Clause report
yanggeng1995/GAN-TTS 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

5 samples harvested; 2 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
3unverified

Licence: 4 of the 5 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

normalize_signal mbinkowski/DeepSpeechDistances/preprocessing.py official repository unverified Apache-2.0 (permissive) · d427fbdc46645d33 · report
dynamic_range_compression izzajalandoni/tts_models/audio_processing.py community (archive-listed) ran · our draft was wrong fingerprinted BSD-3-Clause recorded; this copy not marked cleared · pointer only · 83e2c862f7374ac7 · report
griffin_lim izzajalandoni/tts_models/audio_processing.py community (archive-listed) ran · our draft was wrong BSD-3-Clause recorded; this copy not marked cleared · pointer only · 9f9ec26d4cdfdf7d · report
apply_gradient_allreduce izzajalandoni/tts_models/distributed.py community (archive-listed) unverified BSD-3-Clause recorded; this copy not marked cleared · pointer only · f7bf9f0265e33cf0 · report
load_checkpoint identical code first harvested elsewhere unverified licence of this copy not recorded · f443ef0155d2d898 · report

Tasks

Speech SynthesisText to SpeechVocal Bursts Intensity Predictiontext-to-speech

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: Conditional DBlock, DBlock, GAN-TTS, GBlock, Multiple Random Window Discriminator

1x1 ConvolutionAdamAverage PoolingBatch NormalizationConditional Batch NormalizationConditional DBlockConvolutionDBlockDense ConnectionsDilated Causal ConvolutionDilated ConvolutionFeedforward NetworkGAN-TTSGBlockLinear LayerMixture of Logistic DistributionsMultiple Random Window DiscriminatorOff-Diagonal Orthogonal RegularizationOrthogonal RegularizationReLUResidual ConnectionSpectral NormalizationTanh ActivationWaveNet

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