Papers › Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search

Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search

22 May 2020NeurIPS 2020 12arXiv:2005.11129archive 2025-07-28

Jaehyeon Kim, Sungwon Kim, Jungil Kong, Sungroh Yoon

Recently, text-to-speech (TTS) models such as FastSpeech and ParaNet have been proposed to generate mel-spectrograms from text in parallel. Despite the advantages, the parallel TTS models cannot be trained without guidance from autoregressive TTS models as their external aligners. In this work, we propose Glow-TTS, a flow-based generative model for parallel TTS that does not require any external aligner. We introduce Monotonic Alignment Search (MAS), an internal alignment search algorithm for training Glow-TTS. By leveraging the properties of flows, MAS searches for the most probable monotonic alignment between text and the latent representation of speech. Glow-TTS obtains an order-of-magnitude speed-up over the autoregressive TTS model, Tacotron 2, at synthesis with comparable speech quality, requiring only 1.5 seconds to synthesize one minute of speech in end-to-end. We further show that our model can be easily extended to a multi-speaker setting. Our demo page and code are available at public.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2005.11129")

Code

Syntology Ran 8 of 14 code samples harvested from 2 repositories linked to this paper; 6 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 6 ran with no contract checked.

By repository: community (archive-listed): 14 samples from 2 repositories, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jaywalnut310/glow-tts officialmentioned on GitHubpytorchMIT report
ankurdhuriya/multispeaker-glow-tts mentioned on GitHubpytorchMIT report
coqui-ai/TTS mentioned on GitHubpytorchMPL-2.0 report
revsic/tf-glow-tts mentioned on GitHubtfMIT report
supertone-inc/super-monotonic-align mentioned on GitHubpytorchMIT 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

14 samples harvested; 8 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
6ran
6unverified

Licence: 0 of the 14 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. “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.

basic_cleaners ankurdhuriya/multispeaker-glow-tts/text/cleaners.py community (archive-listed) ran fingerprinted MIT (permissive) · a3a74a14c1d23fbb · report
collapse_whitespace ankurdhuriya/multispeaker-glow-tts/text/cleaners.py community (archive-listed) ran fingerprinted MIT (permissive) · 7669c05d620e883e · report
dynamic_range_compression ankurdhuriya/multispeaker-glow-tts/audio_processing.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 83e2c862f7374ac7 · report
griffin_lim ankurdhuriya/multispeaker-glow-tts/audio_processing.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 9f9ec26d4cdfdf7d · report
latest_checkpoint_path ankurdhuriya/multispeaker-glow-tts/utils.py community (archive-listed) ran MIT (permissive) · 321604dda57bb02d · report
load_state revsic/tf-glow-tts/config.py community (archive-listed) ran MIT (permissive) · a93e65374343828b · report
mask_from_len ankurdhuriya/multispeaker-glow-tts/monotonic_align/monotonic_align/mas.py community (archive-listed) ran MIT (permissive) · f7da3590296389c4 · report
mask_from_lens ankurdhuriya/multispeaker-glow-tts/monotonic_align/monotonic_align/mas.py community (archive-listed) ran MIT (permissive) · af9a236f8ff4a594 · report
duration_loss ankurdhuriya/multispeaker-glow-tts/commons.py community (archive-listed) unverified MIT (permissive) · 2b6c52ad9b61c287 · report
intersperse ankurdhuriya/multispeaker-glow-tts/commons.py community (archive-listed) unverified MIT (permissive) · c01a3efb274ff778 · report
load_checkpoint ankurdhuriya/multispeaker-glow-tts/utils.py community (archive-listed) unverified MIT (permissive) · a4324b03a174abb9 · report
lowercase ankurdhuriya/multispeaker-glow-tts/text/cleaners.py community (archive-listed) unverified MIT (permissive) · 296274b940cb0b32 · report
mle_loss ankurdhuriya/multispeaker-glow-tts/commons.py community (archive-listed) unverified MIT (permissive) · 77759e4586956310 · report
plot_spectrogram_to_numpy ankurdhuriya/multispeaker-glow-tts/utils.py community (archive-listed) unverified MIT (permissive) · 9dc202f235585e84 · report

Tasks

Text to SpeechText-To-Speech Synthesistext-to-speech

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-To-Speech Synthesis LJSpeech Glow-TTS + HiFiGAN Audio Quality MOS 4.34 #4 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

Introduced by this paper: Glow-TTS

Activation NormalizationAffine CouplingGLOWGlow-TTSInvertible 1x1 ConvolutionNormalizing Flows

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