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 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="1803.09017")

Code

Syntology Ran 6 of 21 code samples harvested from 6 repositories linked to this paper; 15 have no recorded run. Of those that ran: 4 ran · our draft was wrong; 1 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: community (archive-listed): 20 samples from 6 repositories, 5 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.

KinglittleQ/GST-Tacotron mentioned on GitHubpytorch report
Kyubyong/expressive_tacotron mentioned on GitHubtf report
acetylSv/GST-tacotron mentioned on GitHubtf report
cnlinxi/style-token_tacotron2 mentioned on GitHubtfMIT report
foamliu/GST-Tacotron-v2 mentioned on GitHubpytorchMIT report
hash2430/pitchtron mentioned on GitHubpytorchNOASSERTION report
syang1993/gst-tacotron mentioned on GitHubtf report
jinhan/tacotron2-gst pytorchBSD-3-Clause 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

21 samples harvested; 6 ran; 0 honoured the contract we drafted; 15 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.

4ran · our draft was wrong
1ran · fixture could not drive it
1ran
15unverified

Licence: 7 of the 21 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 6 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.

dynamic_range_compression foamliu/GST-Tacotron-v2/audio_processing.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 83e2c862f7374ac7 · report
fused_add_tanh_sigmoid_multiply foamliu/GST-Tacotron-v2/glow.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · b38f9c28c5117398 · report
griffin_lim jinhan/tacotron2-gst/audio_processing.py community (archive-listed) ran · our draft was wrong BSD-3-Clause recorded; this copy not marked cleared · pointer only · 9f9ec26d4cdfdf7d · report
looper Kyubyong/expressive_tacotron/synthesize.py community (archive-listed) ran · our draft was wrong fingerprinted no licence file found · pointer only · 3494c70cf20413e6 · report
remove foamliu/GST-Tacotron-v2/glow.py community (archive-listed) ran MIT (permissive) · b13a72233912c0b1 · report
Get_Path CODEJIN/GST_Tacotron/Get_Path.py community (archive-listed) unverified MIT (permissive) · 6611d63ef3343fb1 · report
apply_gradient_allreduce jinhan/tacotron2-gst/distributed.py community (archive-listed) unverified BSD-3-Clause recorded; this copy not marked cleared · pointer only · 8b84f60b5ff9e153 · report
conversion_helper jinhan/tacotron2-gst/fp16_optimizer.py community (archive-listed) unverified BSD-3-Clause recorded; this copy not marked cleared · pointer only · f887d5ffcbc6ad3b · report
fp16_to_fp32 jinhan/tacotron2-gst/fp16_optimizer.py community (archive-listed) unverified BSD-3-Clause recorded; this copy not marked cleared · pointer only · 38034aa1d784464d · report
fp32_to_fp16 jinhan/tacotron2-gst/fp16_optimizer.py community (archive-listed) unverified BSD-3-Clause recorded; this copy not marked cleared · pointer only · ea22baceb9a219a1 · report
griffin_lim foamliu/GST-Tacotron-v2/audio_processing.py community (archive-listed) unverified MIT (permissive) · e274cfa39f3d6bf9 · report
inv_preemphasis cnlinxi/style-token_tacotron2/datasets/audio.py community (archive-listed) unverified MIT (permissive) · bd89c559f716b290 · report
inv_preemphasis CODEJIN/GST_Tacotron/Audio.py community (archive-listed) unverified MIT (permissive) · f1b4c5cfbaef7ff5 · report
is_mulaw cnlinxi/style-token_tacotron2/wavenet_vocoder/util.py community (archive-listed) unverified MIT (permissive) · 203a81d997da01e5 · report
is_mulaw_quantize cnlinxi/style-token_tacotron2/wavenet_vocoder/util.py community (archive-listed) unverified MIT (permissive) · 9f7f281fd2dc3db3 · report
is_raw cnlinxi/style-token_tacotron2/wavenet_vocoder/util.py community (archive-listed) unverified MIT (permissive) · 0ce2fef6ac56c0bd · report
load_model KinglittleQ/GST-Tacotron/generate.py community (archive-listed) unverified MIT (permissive) · d3e8204b867d34ac · report
norm_data cnlinxi/style-token_tacotron2/preprocess.py community (archive-listed) unverified MIT (permissive) · ae38e046c059c78f · report
preemphasis cnlinxi/style-token_tacotron2/datasets/audio.py community (archive-listed) unverified MIT (permissive) · 56a333de6e89087a · report
preemphasis CODEJIN/GST_Tacotron/Audio.py community (archive-listed) unverified MIT (permissive) · 31d5837f91baf6c1 · report
split_func identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · b1491d3c2e709fdc · report

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