Papers › Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech

Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech

13 May 2021arXiv:2105.06337archive 2025-07-28

Vadim Popov, Ivan Vovk, Vladimir Gogoryan, Tasnima Sadekova, Mikhail Kudinov

Recently, denoising diffusion probabilistic models and generative score matching have shown high potential in modelling complex data distributions while stochastic calculus has provided a unified point of view on these techniques allowing for flexible inference schemes. In this paper we introduce Grad-TTS, a novel text-to-speech model with score-based decoder producing mel-spectrograms by gradually transforming noise predicted by encoder and aligned with text input by means of Monotonic Alignment Search. The framework of stochastic differential equations helps us to generalize conventional diffusion probabilistic models to the case of reconstructing data from noise with different parameters and allows to make this reconstruction flexible by explicitly controlling trade-off between sound quality and inference speed. Subjective human evaluation shows that Grad-TTS is competitive with state-of-the-art text-to-speech approaches in terms of Mean Opinion Score. We will make the code publicly available shortly.

PaperPDFCodeCode 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="2105.06337")

Code

Syntology Ran 9 of 18 code samples harvested from 2 repositories linked to this paper; 9 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · violated contract; 5 ran · our draft was wrong; 1 ran with no contract checked.

By repository: community (archive-listed): 17 samples from 2 repositories, 8 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.

huawei-noah/Speech-Backbones officialmentioned in papermentioned on GitHubpytorch report
WelkinYang/GradTTS mentioned on GitHubpytorchMIT report
majidAdibian77/ResGrad mentioned on GitHubpytorchMIT report
playvoice/grad-svc 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

18 samples harvested; 9 ran; 1 honoured the contract we drafted; 9 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.

1ran · honoured contract
2ran · violated contract
5ran · our draft was wrong
1ran
9unverified

Licence: 1 of the 18 samples is 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.

default WelkinYang/GradTTS/unet.py community (archive-listed) ran · violated contract MIT (permissive) · fbf9ec7be545688e · report
dynamic_range_compression WelkinYang/GradTTS/audio_processing.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 83e2c862f7374ac7 · report
exists WelkinYang/GradTTS/unet.py community (archive-listed) ran · violated contract MIT (permissive) · 608e364a9d2376a3 · report
griffin_lim WelkinYang/GradTTS/audio_processing.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 9f9ec26d4cdfdf7d · report
latest_checkpoint_path WelkinYang/GradTTS/utils.py community (archive-listed) ran MIT (permissive) · 321604dda57bb02d · report
load_bigv_model playvoice/grad-svc/gvc_inference.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 98cc9f3aed7a8480 · report
load_gvc_model playvoice/grad-svc/gvc_inference.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 051895a532dbea48 · report
num_to_groups WelkinYang/GradTTS/unet.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 4f66ae7f14b3b240 · report
duration_loss WelkinYang/GradTTS/commons.py community (archive-listed) unverified MIT (permissive) · 2b6c52ad9b61c287 · report
expand_abbreviations WelkinYang/GradTTS/text/cleaners.py community (archive-listed) unverified MIT (permissive) · cea1f83e9db28ed8 · report
expand_numbers WelkinYang/GradTTS/text/cleaners.py community (archive-listed) unverified MIT (permissive) · 4c6716f6a3894fe8 · report
intersperse WelkinYang/GradTTS/commons.py community (archive-listed) unverified MIT (permissive) · c01a3efb274ff778 · report
load_checkpoint WelkinYang/GradTTS/utils.py community (archive-listed) unverified MIT (permissive) · a4324b03a174abb9 · report
lowercase WelkinYang/GradTTS/text/cleaners.py community (archive-listed) unverified MIT (permissive) · 296274b940cb0b32 · report
mle_loss WelkinYang/GradTTS/commons.py community (archive-listed) unverified MIT (permissive) · 7e3430bd9ded8745 · report
plot_spectrogram_to_numpy WelkinYang/GradTTS/utils.py community (archive-listed) unverified MIT (permissive) · 9dc202f235585e84 · report
update_model WelkinYang/GradTTS/waveglow/convert_model.py community (archive-listed) unverified MIT (permissive) · 22c86725da4140b0 · report
read_lexicon identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 2b5c06c1ba593c3c · report

Tasks

DecoderSpeech SynthesisText to SpeechText-To-Speech Synthesistext-to-speech

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-To-Speech Synthesis LJSpeech Grad-TTS + HiFiGAN (1000 steps) Audio Quality MOS 4.37 #3 of 16 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Diffusion

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