Papers › FastSpeech: Fast, Robust and Controllable Text to Speech

FastSpeech: Fast, Robust and Controllable Text to Speech

22 May 2019NeurIPS 2019 12arXiv:1905.09263archive 2025-07-28

Yi Ren, Yangjun Ruan, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, Tie-Yan Liu

Neural network based end-to-end text to speech (TTS) has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron 2) usually first generate mel-spectrogram from text, and then synthesize speech from the mel-spectrogram using vocoder such as WaveNet. Compared with traditional concatenative and statistical parametric approaches, neural network based end-to-end models suffer from slow inference speed, and the synthesized speech is usually not robust (i.e., some words are skipped or repeated) and lack of controllability (voice speed or prosody control). In this work, we propose a novel feed-forward network based on Transformer to generate mel-spectrogram in parallel for TTS. Specifically, we extract attention alignments from an encoder-decoder based teacher model for phoneme duration prediction, which is used by a length regulator to expand the source phoneme sequence to match the length of the target mel-spectrogram sequence for parallel mel-spectrogram generation. Experiments on the LJSpeech dataset show that our parallel model matches autoregressive models in terms of speech quality, nearly eliminates the problem of word skipping and repeating in particularly hard cases, and can adjust voice speed smoothly. Most importantly, compared with autoregressive Transformer TTS, our model speeds up mel-spectrogram generation by 270x and the end-to-end speech synthesis by 38x. Therefore, we call our model FastSpeech.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 11 code samples: 10 from 4 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 11: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 10 samples from 4 repositories, 9 ran (7 with no instrument failure; 2 where Syntology's instrument failed); 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.

No sample is linked to this paper from 12 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 10 samples that ran has no recorded date.

22 repositories listed; official and paper-mentioned ones first.

as-ideas/TransformerTTS mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
as-ideas/deepforcedaligner mentioned on GitHubpytorchMITSyntology: 7 samples, 7 ran (0 instrument-failed) · 0 unverified report
bloodraven66/deepforcedaligner mentioned on GitHubpytorchMITSyntology: 1 sample, 0 ran · 1 unverified report
cadia-lvl/fastspeech2 mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FastSpeech 2: Fast and High-Quality End-to-End Text to Speech (arXiv:2006.04558; that paper's own run record: 83 ran (of which 27 constructed an object rather than computing a result; 70 with no instrument failure: 9 honoured, 1 violated, 60 with no contract checked; 13 where Syntology's instrument failed) · 36 unverified); nothing checks that they implement this paper's method. report
coqui-ai/TTS mentioned on GitHubpytorchMPL-2.0Syntology: not harvested report
dathudeptrai/TensorflowTTS mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FastSpeech 2: Fast and High-Quality End-to-End Text to Speech (arXiv:2006.04558; that paper's own run record: 83 ran (of which 27 constructed an object rather than computing a result; 70 with no instrument failure: 9 honoured, 1 violated, 60 with no contract checked; 13 where Syntology's instrument failed) · 36 unverified); nothing checks that they implement this paper's method. report
erasedwalt/FastSpeech mentioned on GitHubpytorchSyntology: not harvested report
ga642381/FastSpeech2 mentioned on GitHubpytorchSyntology: not harvested report
jkyunnng/happyquokka_system_for_eeg_challenge mentioned on GitHubpytorchSyntology: not harvested report
kdaip/stabletts mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FiLM: Visual Reasoning with a General Conditioning Layer (arXiv:1709.07871; that paper's own run record: 9 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
ming024/FastSpeech2 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified); nothing checks that they implement this paper's method. report
rishikksh20/FastSpeech2 mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
rishikksh20/LightSpeech mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search (arXiv:2102.04040; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
tartunlp/transformertts mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FastSpeech 2: Fast and High-Quality End-to-End Text to Speech (arXiv:2006.04558; that paper's own run record: 83 ran (of which 27 constructed an object rather than computing a result; 70 with no instrument failure: 9 honoured, 1 violated, 60 with no contract checked; 13 where Syntology's instrument failed) · 36 unverified); nothing checks that they implement this paper's method. report
xcmyz/FastSpeech mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified); nothing checks that they implement this paper's method. report
2023-MindSpore-1/ms-code-15 mindsporeSyntology: not harvested report
PaddlePaddle/PaddleSpeech paddleApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A³T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing (arXiv:2203.09690; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
keonlee9420/Comprehensive-Transformer-TTS pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FastSpeech 2: Fast and High-Quality End-to-End Text to Speech (arXiv:2006.04558; that paper's own run record: 83 ran (of which 27 constructed an object rather than computing a result; 70 with no instrument failure: 9 honoured, 1 violated, 60 with no contract checked; 13 where Syntology's instrument failed) · 36 unverified); nothing checks that they implement this paper's method. report
keonlee9420/Expressive-FastSpeech2 pytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
keonlee9420/PortaSpeech pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PortaSpeech: Portable and High-Quality Generative Text-to-Speech (arXiv:2109.15166; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
keonlee9420/STYLER pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FastSpeech 2: Fast and High-Quality End-to-End Text to Speech (arXiv:2006.04558; that paper's own run record: 83 ran (of which 27 constructed an object rather than computing a result; 70 with no instrument failure: 9 honoured, 1 violated, 60 with no contract checked; 13 where Syntology's instrument failed) · 36 unverified); nothing checks that they implement this paper's method. report
keonlee9420/StyleSpeech pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation (arXiv:2106.03153; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

11 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
7ran
1unverified

Licence: 3 of the 11 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 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. 1 sample is listed last, in a group without a repository. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

as-ideas/deepforcedaligner community (archive-listed) 7 samples, 7 ran (0 instrument-failed) · 0 unverified
collate_dataset dfa/dataset.py ran MIT (permissive) · 63a432b575d3d1fd · report fixture: signature batch:list/1/dict · returned dict · level recorded 2026-09-24
from_node_index dfa/duration_extraction.py ran fingerprinted MIT (permissive) · 7c54f74423ae2ae2 · report fixture: signature node_index:int/0/int, cols:int/0/int · returned tuple · level recorded 2026-09-24
get_files in 30 papers dfa/utils.py ran MIT (permissive) · 8ff429bfc952ac29 · report fixture: signature path:str/0/str, extension:str/0/str · returned list · level recorded 2026-09-24
read_config in 49 papers dfa/utils.py ran MIT (permissive) · 18b04be71b1d8e19 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-24
read_metafile dfa/utils.py ran MIT (permissive) · 76da406d31f0074d · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-24
to_adj_matrix dfa/duration_extraction.py ran MIT (permissive) · 225cb1b140f846ff · report fixture: signature mat:ndarray/2/float · returned csr_matrix · level recorded 2026-09-24
to_node_index dfa/duration_extraction.py ran fingerprinted MIT (permissive) · a2ea77bb519c9fc7 · report fixture: signature i:int/0/int, j:int/0/int, cols:int/0/int · returned int · level recorded 2026-09-24
bloodraven66/deepforcedaligner community (archive-listed) 1 sample, 0 ran · 1 unverified
read_metafile dfa/utils.py unverified MIT (permissive) · 9ca6411791cad183 · report
rishikksh20/FastSpeech2 community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
process_paragraph inference.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong fingerprinted licence of this copy not recorded · 141ed5512c50d7db · report fixture: signature para:str/0/str · returned list · level recorded 2026-09-22
keonlee9420/Expressive-FastSpeech2 community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
read_lexicon in 16 papers synthesize.py ran · our draft was wrong licence not identified · pointer only · e68a2e13d0cbe0f9 · report fixture: signature lex_path:str/0/str · returned dict · level recorded 2026-09-22
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
read_lexicon in 16 papers repository not located ran · our draft was wrong licence of this copy not recorded · 2b5c06c1ba593c3c · report fixture: signature lex_path:str/0/str · returned dict · level recorded, date not recorded

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 FastSpeech (Mel + WaveGlow) Audio Quality MOS 3.84 #10 of 16 Archive leaderboard report
Text-To-Speech Synthesis LJSpeech Merlin Audio Quality MOS 2.4 #12 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

Absolute Position EncodingsAdamAttentionBPEBatch NormalizationConvolutionDense ConnectionsDilated Causal ConvolutionDropoutLabel SmoothingLayer NormalizationLinear LayerMax PoolingMixture of Logistic DistributionsMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSPEEDSigmoid ActivationSoftmaxTanh ActivationTransformerWaveNet

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