Papers › Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis

Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis

23 Mar 2018ICML 2018 7arXiv:1803.09017archive 2025-07-28

Yuxuan Wang, Daisy Stanton, Yu Zhang, RJ Skerry-Ryan, Eric Battenberg, Joel Shor, Ying Xiao, Fei Ren, Ye Jia, Rif A. Saurous

In this work, we propose "global style tokens" (GSTs), a bank of embeddings that are jointly trained within Tacotron, a state-of-the-art end-to-end speech synthesis system. The embeddings are trained with no explicit labels, yet learn to model a large range of acoustic expressiveness. GSTs lead to a rich set of significant results. The soft interpretable "labels" they generate can be used to control synthesis in novel ways, such as varying speed and speaking style - independently of the text content. They can also be used for style transfer, replicating the speaking style of a single audio clip across an entire long-form text corpus. When trained on noisy, unlabeled found data, GSTs learn to factorize noise and speaker identity, providing a path towards highly scalable but robust speech synthesis.

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 21 code samples: 20 from 6 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 21: 19 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 20 samples from 6 repositories, 18 ran (13 with no instrument failure; 5 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 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

KinglittleQ/GST-Tacotron mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
Kyubyong/expressive_tacotron mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
acetylSv/GST-tacotron mentioned on GitHubtfSyntology: not harvested report
cnlinxi/style-token_tacotron2 mentioned on GitHubtfMITSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
foamliu/GST-Tacotron-v2 mentioned on GitHubpytorchMITSyntology: 4 samples, 4 ran (3 instrument-failed) · 0 unverified report
hash2430/pitchtron mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
syang1993/gst-tacotron mentioned on GitHubtfSyntology: not harvested report
CODEJIN/GST_Tacotron tfMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified 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
jinhan/tacotron2-gst pytorchBSD-3-ClauseSyntology: 5 samples, 5 ran (1 instrument-failed) · 0 unverified report
keonlee9420/Cross-Speaker-Emotion-Transfer pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable... (arXiv:2103.14574; that paper's own run record: 2 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; 0 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

21 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 6 where Syntology's instrument failed) · 2 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.

5ran · our draft was wrong
1ran; the contract check could not run
13ran
2unverified

Licence: 9 of the 21 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 6 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 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.

KinglittleQ/GST-Tacotron community (archive-listed) 1 sample, 0 ran · 1 unverified
load_model in 479 papers generate.py unverified MIT (permissive) · d3e8204b867d34ac · report
Kyubyong/expressive_tacotron community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
looper synthesize.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 3494c70cf20413e6 · report fixture: signature ref:ndarray/3/float, start:int/0/int, batch_size:int/0/int · returned tuple · level recorded 2026-09-22
cnlinxi/style-token_tacotron2 community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
inv_preemphasis datasets/audio.py ran MIT (permissive) · bd89c559f716b290 · report fixture: signature wav:ndarray/1/float, k:float/0/float, inv_preemphasize:bool/0/bool · returned ndarray · level recorded 2026-09-25
is_mulaw wavenet_vocoder/util.py ran MIT (permissive) · 203a81d997da01e5 · report fixture: signature s:str/0/str · returned bool · level recorded 2026-09-26
is_mulaw_quantize wavenet_vocoder/util.py ran MIT (permissive) · 9f7f281fd2dc3db3 · report fixture: signature s:str/0/str · returned bool · level recorded 2026-09-26
is_raw wavenet_vocoder/util.py ran MIT (permissive) · 0ce2fef6ac56c0bd · report fixture: signature s:str/0/str · returned bool · level recorded 2026-09-26
preemphasis datasets/audio.py ran MIT (permissive) · 56a333de6e89087a · report fixture: signature wav:ndarray/1/float, k:float/0/float, preemphasize:bool/0/bool · returned ndarray · level recorded 2026-09-25
norm_data preprocess.py unverified MIT (permissive) · ae38e046c059c78f · report
foamliu/GST-Tacotron-v2 community (archive-listed) 4 samples, 4 ran (3 instrument-failed) · 0 unverified
dynamic_range_compression in 31 papers audio_processing.py ran · our draft was wrong fingerprinted MIT (permissive) · 83e2c862f7374ac7 · report fixture: signature x:Tensor/2/float, C:int/0/int, clip_val:float/0/float · returned Tensor · level recorded 2026-09-22
fused_add_tanh_sigmoid_multiply in 11 papers glow.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) here; the stored copy is pointer only · b38f9c28c5117398 · report fixture: returned Tensor · level recorded 2026-09-22
griffin_lim in 16 papers audio_processing.py ran MIT (permissive) · e274cfa39f3d6bf9 · report fixture: signature magnitudes:Tensor/3/float, stft_fn:MockSTFT/0/?, n_iters:int/0/int · returned Tensor · level recorded 2026-09-26
remove in 8 papers glow.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · b13a72233912c0b1 · report fixture: signature conv_list:callable/0/? · returned ModuleList · level recorded 2026-09-22
CODEJIN/GST_Tacotron community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
Get_Path Get_Path.py ran MIT (permissive) · 6611d63ef3343fb1 · report fixture: signature sample_count:int/0/int · returned tuple · level recorded 2026-09-26
inv_preemphasis Audio.py ran fingerprinted MIT (permissive) · f1b4c5cfbaef7ff5 · report fixture: signature x:ndarray/1/float, preemphasis:float/0/float · returned ndarray · level recorded 2026-09-26
preemphasis Audio.py ran fingerprinted MIT (permissive) · 31d5837f91baf6c1 · report fixture: signature x:ndarray/1/float, preemphasis:float/0/float · returned ndarray · level recorded 2026-09-26
jinhan/tacotron2-gst community (archive-listed) 5 samples, 5 ran (1 instrument-failed) · 0 unverified
apply_gradient_allreduce in 12 papers distributed.py ran BSD-3-Clause recorded; this copy not marked cleared · pointer only · 8b84f60b5ff9e153 · report fixture: signature module:callable/0/? · returned SimpleModel · level recorded 2026-09-26
conversion_helper in 5 papers fp16_optimizer.py ran BSD-3-Clause recorded; this copy not marked cleared · pointer only · f887d5ffcbc6ad3b · report fixture: signature val:list/1/int, conversion:callable/0/? · returned list · level recorded 2026-09-25
fp16_to_fp32 in 5 papers fp16_optimizer.py ran fingerprinted BSD-3-Clause recorded; this copy not marked cleared · pointer only · 38034aa1d784464d · report fixture: signature val:tuple/1/Tensor · returned tuple · level recorded 2026-09-25
fp32_to_fp16 in 5 papers fp16_optimizer.py ran fingerprinted BSD-3-Clause recorded; this copy not marked cleared · pointer only · ea22baceb9a219a1 · report fixture: signature val:tuple/1/Tensor · returned tuple · level recorded 2026-09-25
griffin_lim in 16 papers audio_processing.py ran · our draft was wrong BSD-3-Clause recorded; this copy not marked cleared · pointer only · 9f9ec26d4cdfdf7d · report fixture: signature magnitudes:Tensor/3/float, stft_fn:STFT/0/?, n_iters:int/0/int · returned Tensor · 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.
split_func repository not located ran · our draft was wrong licence of this copy not recorded · b1491d3c2e709fdc · report fixture: signature x:Tensor/2/float, split_pos:Tensor/1/int · returned list · level recorded 2026-09-22

Tasks

Speech SynthesisStyle TransferText-To-Speech Synthesis

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Batch NormalizationBiGRUCBHGConvolutionDense ConnectionsDropoutGRUGriffin-Lim AlgorithmHighway LayerHighway NetworkMax PoolingReLUResidual ConnectionResidual GRUSPEEDSigmoid ActivationTacotronTanh Activation

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