Papers › Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

11 Jun 2021arXiv:2106.06103links table onlyarchive 2025-07-28

Jaehyeon Kim, Jungil Kong, Juhee Son

The archive published only this paper's code-link row. Authors, date and abstract are from arXiv's metadata (CC0), read from the Kaggle arXiv metadata snapshot of 2026-09-12 where its title matched the archive's; the title is the archive's.

Several recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems. In this work, we present a parallel end-to-end TTS method that generates more natural sounding audio than current two-stage models. Our method adopts variational inference augmented with normalizing flows and an adversarial training process, which improves the expressive power of generative modeling. We also propose a stochastic duration predictor to synthesize speech with diverse rhythms from input text. With the uncertainty modeling over latent variables and the stochastic duration predictor, our method expresses the natural one-to-many relationship in which a text input can be spoken in multiple ways with different pitches and rhythms. A subjective human evaluation (mean opinion score, or MOS) on the LJ Speech, a single speaker dataset, shows that our method outperforms the best publicly available TTS systems and achieves a MOS comparable to ground truth.

PaperPDFCodeCode Syntology ranMethod as code

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 77 code samples: 76 from 9 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 77: 47 ran (of which 12 constructed an object rather than computing a result; 34 with no instrument failure: 2 honoured, 0 violated, 32 with no contract checked; 13 where Syntology's instrument failed) · 30 unverified. Where Syntology's instrument failed: 9 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 8 ran (7 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 50 samples from 6 repositories, 29 ran (21 with no instrument failure; 8 where Syntology's instrument failed); found in paper text by Syntology: 15 samples from 2 repositories, 9 ran (6 with no instrument failure; 3 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 7 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.

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

jaywalnut310/vits officialmentioned in papermentioned on GitHubpytorchMITSyntology: 11 samples, 8 ran (1 instrument-failed) · 3 unverified report
coqui-ai/TTS mentioned on GitHubpytorchMPL-2.0Syntology: not harvested report
daniilrobnikov/vits2 mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality (arXiv:2205.04421; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
isletennos/mmvc_trainer mentioned on GitHubpytorchSyntology: 23 samples, 15 ran (5 instrument-failed) · 8 unverified report
jmp84/vits mentioned on GitHubpytorchSyntology: 12 samples, 6 ran (2 instrument-failed) · 6 unverified report
k2-fsa/icefall mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unifying Streaming and Non-streaming Zipformer-based ASR (arXiv:2506.14434; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
lakahaga/dc-comix-tts mentioned on GitHubpytorchSyntology: not harvested report
maum-ai/phaseaug mentioned on GitHubpytorchBSD-3-ClauseSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
mindslab-ai/phaseaug mentioned on GitHubpytorchBSD-3-ClauseSyntology: not harvested report
olawod/freevc mentioned on GitHubpytorchSyntology: 7 samples, 2 ran (0 instrument-failed) · 5 unverified report
open-creator/icefall mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Robust Speech Recognition via Large-Scale Weak Supervision (arXiv:2212.04356; that paper's own run record: 49 ran (of which 0 constructed an object rather than computing a result; 36 with no instrument failure: 4 honoured, 1 violated, 31 with no contract checked; 13 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
p0p4k/vits2_pytorch mentioned on GitHubpytorchMITSyntology: 1 sample, 0 ran · 1 unverified report
wenet-e2e/wetts mentioned on GitHubpytorchApache-2.0Syntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
ylacombe/finetune-hf-vits mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Scaling Speech Technology to 1,000+ Languages (arXiv:2305.13516; 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
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
pwc-1/Paper-9 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RandAugment: Practical automated data augmentation with a reduced search space (arXiv:1909.13719; that paper's own run record: 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 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

77 samples harvested: 47 ran (of which 12 constructed an object rather than computing a result; 34 with no instrument failure: 2 honoured, 0 violated, 32 with no contract checked; 13 where Syntology's instrument failed) · 30 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
9ran · our draft was wrong
4ran; the contract check could not run
32ran
30unverified

Licence: 35 of the 77 samples are pointer only, meaning Syntology does not serve that copy's text. For 11 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 9 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”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

jaywalnut310/vits official repository 11 samples, 8 ran (1 instrument-failed) · 3 unverified
discriminator_loss in 38 papers losses.py ran MIT (permissive) here; the stored copy is pointer only · 896f7aae82a62114 · report fixture: signature disc_real_outputs:list/1/Tensor, disc_generated_outputs:list/1/Tensor · returned tuple · level recorded 2026-09-26
dynamic_range_compression_torch in 9 papers mel_processing.py ran fingerprinted MIT (permissive) · 262807b9eb9706a5 · report fixture: signature x:Tensor/2/float, C:int/0/int, clip_val:float/0/float · returned Tensor · level recorded 2026-09-26
dynamic_range_decompression_torch in 5 papers mel_processing.py ran fingerprinted MIT (permissive) · 78c12e563d5af53d · report fixture: signature x:Tensor/2/float, C:int/0/int · returned Tensor · level recorded 2026-09-26
feature_loss in 27 papers losses.py ran MIT (permissive) here; the stored copy is pointer only · 24e8b4731dc3e070 · report fixture: signature fmap_r:list/1/list, fmap_g:list/1/list · returned Tensor · level recorded 2026-09-26
generator_loss in 32 papers losses.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 6191fd9efbdd55d4 · report fixture: signature disc_outputs:list/1/Tensor · returned tuple · level recorded 2026-09-26
load_checkpoint in 277 papers utils.py ran MIT (permissive) here; the stored copy is pointer only · c647283e53cacacf · report fixture: signature checkpoint_path:str/0/str, model:callable/0/?, optimizer:Adam/0/? · returned tuple · level recorded 2026-09-24
spectral_normalize_torch in 8 papers mel_processing.py ran fingerprinted MIT (permissive) · 26b87488d429896a · report fixture: signature magnitudes:Tensor/2/float · returned Tensor · level recorded 2026-09-26
unconstrained_rational_quadratic_spline in 8 papers transforms.py ran MIT (permissive) here; the stored copy is pointer only · 70a7614b3b3eb41f · report fixture: signature inputs:Tensor/1/float, unnormalized_widths:Tensor/2/float, unnormalized_heights:Tensor/2/float, unnormalized_derivatives:Tensor/2/float, inverse:bool/0/bool, tails:str/0/str, tail_bound:float/0/float, min_bin_width:float/0/float, min_bin_height:float/0/float, min_derivative:float/0/float · returned tuple · level recorded 2026-09-24
piecewise_rational_quadratic_transform in 8 papers transforms.py unverified MIT (permissive) here; the stored copy is pointer only · ba6cafc4d658c14f · report
plot_spectrogram_to_numpy in 8 papers utils.py unverified MIT (permissive) · d1de5b72a4f78810 · report
searchsorted in 9 papers transforms.py unverified MIT (permissive) · e85d747983c4f5d8 · report
isletennos/mmvc_trainer community (archive-listed) 23 samples, 15 ran (5 instrument-failed) · 8 unverified
FFN in 37 papers models.py ran · metamorphic tier: deterministic no licence file found · pointer only · 105de269bbc6a61f · report fixture: returned FFN · level recorded 2026-09-22
Flip models.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 1792455895b131d4 · report fixture: signature x:Tensor/2/float, reverse:bool/0/bool · returned tuple · level recorded 2026-09-22
Generator in 95 papers models.py ran · metamorphic tier: deterministic no licence file found · pointer only · ccc7aa1ec0421795 · report fixture: returned Generator · level recorded 2026-09-22
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
models.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 649dfa04ce7522a2 · report fixture: returned LayerNorm · level recorded 2026-09-22
MultiHeadAttention in 124 papers
census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
models.py ran · metamorphic tier: deterministic no licence file found · pointer only · 1565e9cf603643df · report fixture: returned MultiHeadAttention · level recorded 2026-09-22
ResBlock1 models.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 54658cf2627bb592 · report fixture: returned ResBlock1 · level recorded 2026-09-22
ResBlock2 models.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 054d6a8b9d719923 · report fixture: returned ResBlock2 · level recorded 2026-09-22
WN models.py ran · metamorphic tier: deterministic no licence file found · pointer only · c95240fe5270874a · report fixture: returned WN · level recorded 2026-09-22
convert_pad_shape in 15 papers models.py ran · honoured contract no licence file found · pointer only · 59ae0708b1e8d94b · report fixture: signature pad_shape:list/1/list · returned list · level recorded 2026-09-22
fused_add_tanh_sigmoid_multiply in 11 papers models.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · b38f9c28c5117398 · report fixture: returned Tensor · level recorded 2026-09-22
get_padding in 84 papers models.py ran · honoured contract fingerprinted no licence file found · pointer only · a26f85d7c72ef39a · report fixture: signature kernel_size:int/0/int, dilation:int/0/int · returned int · level recorded 2026-09-22
rand_slice_segments models.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 0b891bcd5e4b4be1 · report fixture: signature x:Tensor/3/float, x_lengths:Tensor/1/int, segment_size:int/0/int · returned tuple · level recorded 2026-09-22
slice_segments models.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 5e342f73b3b911ec · report fixture: signature x:Tensor/3/float, ids_str:Tensor/1/int, segment_size:int/0/int · returned Tensor · level recorded 2026-09-22
spectrogram_torch models.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 2a01b8026e5c2bc7 · report fixture: signature y:Tensor/2/float, n_fft:int/0/int, sampling_rate:int/0/int, hop_size:int/0/int, win_size:int/0/int, center:bool/0/bool · returned Tensor · level recorded 2026-09-22
spectrogram_torch_data models.py ran · our draft was wrong no licence file found · pointer only · 08beff5564cff157 · report fixture: signature y:Tensor/2/float, data:DataConfig/0/? · returned Tensor · level recorded 2026-09-22
Encoder in 278 papers models.py unverified no licence file found · pointer only · 62c7b592b2d2297b · report
PosteriorEncoder models.py unverified no licence file found · pointer only · c148debeb5b49924 · report
ResidualCouplingBlock models.py unverified no licence file found · pointer only · 20b53a6e6135c48b · report
ResidualCouplingLayer models.py unverified no licence file found · pointer only · 60a5c0ef9ff2d916 · report
SynthesizerTrn models.py unverified no licence file found · pointer only · c21db10c88a81887 · report
TextEncoder in 11 papers models.py unverified no licence file found · pointer only · 9d5ca7de433e20e7 · report
init_weights in 109 papers models.py unverified no licence file found · pointer only · b6ab401f5185c8e7 · report
maximum_path models.py unverified no licence file found · pointer only · 4f078be04af51043 · report
jmp84/vits community (archive-listed) 12 samples, 6 ran (2 instrument-failed) · 6 unverified
DDSConv models.py ran · metamorphic tier: deterministic MIT (permissive) · f0dbf406caa930d9 · report fixture: returned DDSConv · level recorded 2026-09-22
DurationPredictor models.py ran · metamorphic tier: deterministic MIT (permissive) · d2782997a07f6dfc · report fixture: returned DurationPredictor · level recorded 2026-09-22
ElementwiseAffine models.py ran · metamorphic tier: deterministic MIT (permissive) · d6380a9b9627f5fa · report fixture: returned ElementwiseAffine · level recorded 2026-09-22
Log in 6 papers models.py ran fingerprinted MIT (permissive) · ecedf3198e3c1020 · report fixture: signature x:Tensor/3/float, x_mask:Tensor/3/float, reverse:bool/0/bool · returned tuple · level recorded 2026-09-24
generate_path models.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 6981a5db6f046922 · report fixture: signature duration:Tensor/3/int, mask:Tensor/4/float · returned Tensor · level recorded 2026-09-22
unconstrained_rational_quadratic_spline in 8 papers models.py ran · our draft was wrong MIT (permissive) · 9e31572da16d9de4 · report fixture: signature inputs:Tensor/1/float, unnormalized_widths:Tensor/2/float, unnormalized_heights:Tensor/2/float, unnormalized_derivatives:Tensor/2/float, inverse:bool/0/bool, tails:str/0/str, tail_bound:float/0/float, min_bin_width:float/0/float, min_bin_height:float/0/float, min_derivative:float/0/float · returned tuple · level recorded 2026-09-22
ConvFlow models.py unverified MIT (permissive) · 6121d5117e03763b · report
Generator in 95 papers models.py unverified MIT (permissive) · fa239ec0b64f95b1 · report
StochasticDurationPredictor models.py unverified MIT (permissive) · 76a16536fc995a46 · report
SynthesizerTrn models.py unverified MIT (permissive) · c27a865f5e63bc20 · report
piecewise_rational_quadratic_transform in 8 papers models.py unverified MIT (permissive) · 8e2e7c27501567b6 · report
rational_quadratic_spline models.py unverified MIT (permissive) · b4db05cf916b9553 · report
maum-ai/phaseaug community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
discriminator_loss in 38 papers models.py ran BSD-3-Clause (permissive) · 9aa5905b881a121c · report fixture: signature disc_real_outputs:list/1/Tensor, disc_generated_outputs:list/1/Tensor · returned tuple · level recorded 2026-09-24
feature_loss in 27 papers models.py ran BSD-3-Clause (permissive) here; the stored copy is pointer only · e453b51f0ed5fb28 · report fixture: signature fmap_r:list/1/list, fmap_g:list/1/list · returned Tensor · level recorded 2026-09-24
generator_loss in 32 papers models.py ran · our draft was wrong BSD-3-Clause (permissive) here; the stored copy is pointer only · 1a9d74439d969cfd · report fixture: signature disc_outputs:list/1/Tensor · returned tuple · level recorded 2026-09-24
olawod/freevc community (archive-listed) 7 samples, 2 ran (0 instrument-failed) · 5 unverified
SpeakerEncoder models.py ran · metamorphic tier: deterministic MIT (permissive) · b35a311435634a3e · report fixture: returned SpeakerEncoder · level recorded 2026-09-22
WN models.py ran · metamorphic tier: deterministic MIT (permissive) · 0b63f8b32a435c7e · report fixture: returned WN · level recorded 2026-09-22
Encoder in 278 papers models.py unverified MIT (permissive) · 862e2838890719eb · report
Generator in 95 papers models.py unverified MIT (permissive) · b9e59ecadc84c228 · report
ResidualCouplingBlock models.py unverified MIT (permissive) · 7f154bf0fb8dcbbb · report
ResidualCouplingLayer models.py unverified MIT (permissive) · 1541e569125c52bd · report
SynthesizerTrn models.py unverified MIT (permissive) · f0ac43353f543134 · report
p0p4k/vits2_pytorch community (archive-listed) 1 sample, 0 ran · 1 unverified
weight_norm_modules attentions.py unverified MIT (permissive) · 0c0b5a033fe98758 · report
wenet-e2e/wetts community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
collate_fn in 500 papers wetts/frontend/dataset.py ran Apache-2.0 (permissive) · 4d1471c10a3510b7 · report fixture: signature batch_samples:list/1/dict, tokenizer:callable/0/? · returned tuple · level recorded 2026-09-24
cosine_similarity in 120 papers
census: 26 implementations from 30 papers, 11 distinct outputs across 5 buckets, one shared input per bucket
wetts/frontend/export_onnx.py ran fingerprinted Apache-2.0 (permissive) · 2aa92e480638a500 · report fixture: signature tensor1:Tensor/2/float, tensor2:Tensor/2/float · returned float · level recorded 2026-09-24
read_table in 8 papers wetts/frontend/utils.py ran Apache-2.0 (permissive) · eb2a1b4e5d25755d · report fixture: signature dict_file:str/0/str · returned dict · level recorded 2026-09-24
download in 53 papers wetts/cli/hub.py unverified Apache-2.0 (permissive) · 8886154120adfdf8 · report
NVIDIA/tacotron2 found in paper text by Syntology 6 samples, 2 ran (2 instrument-failed) · 4 unverified
dynamic_range_compression in 31 papers audio_processing.py ran · our draft was wrong fingerprinted BSD-3-Clause (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
griffin_lim in 16 papers audio_processing.py ran · our draft was wrong BSD-3-Clause (permissive) · 9f9ec26d4cdfdf7d · report fixture: signature magnitudes:Tensor/3/float, stft_fn:STFT/0/?, n_iters:int/0/int · returned Tensor · level recorded 2026-09-22
apply_gradient_allreduce in 12 papers distributed.py unverified BSD-3-Clause (permissive) here; the stored copy is pointer only · f7bf9f0265e33cf0 · report
plot_alignment_to_numpy plotting_utils.py unverified BSD-3-Clause (permissive) · 3d89a23ee4d0b639 · report
plot_spectrogram_to_numpy in 8 papers plotting_utils.py unverified BSD-3-Clause (permissive) · 2545971684f8134d · report
save_figure_to_numpy in 7 papers plotting_utils.py unverified BSD-3-Clause (permissive) · 29d749e3e95fa41d · report
jaywalnut310/glow-tts found in paper text by Syntology 9 samples, 7 ran (1 instrument-failed) · 2 unverified
duration_loss commons.py ran fingerprinted MIT (permissive) · 2b6c52ad9b61c287 · report fixture: signature logw:Tensor/2/float, logw_:Tensor/2/float, lengths:Tensor/1/float · returned Tensor · level recorded 2026-09-25
expand_abbreviations in 10 papers text/cleaners.py ran fingerprinted MIT (permissive) · cea1f83e9db28ed8 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
intersperse in 14 papers commons.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · c01a3efb274ff778 · report fixture: signature lst:list/1/int, item:int/0/int · returned list · level recorded 2026-09-26
latest_checkpoint_path in 9 papers utils.py ran MIT (permissive) here; the stored copy is pointer only · 321604dda57bb02d · report fixture: signature dir_path:str/0/str, regex:str/0/str · returned str · level recorded 2026-09-24
load_checkpoint in 277 papers utils.py ran MIT (permissive) · a4324b03a174abb9 · report fixture: signature checkpoint_path:str/0/str, model:callable/0/?, optimizer:SGD/0/? · returned tuple · level recorded 2026-09-25
lowercase in 9 papers text/cleaners.py ran fingerprinted MIT (permissive) · 296274b940cb0b32 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
mle_loss in 6 papers commons.py ran MIT (permissive) · 77759e4586956310 · report fixture: signature z:Tensor/2/float, m:Tensor/2/float, logs:Tensor/2/float, logdet:Tensor/1/float, mask:Tensor/2/float · returned Tensor · level recorded 2026-09-25
expand_numbers in 5 papers text/cleaners.py unverified MIT (permissive) · 4c6716f6a3894fe8 · report
plot_spectrogram_to_numpy in 8 papers utils.py unverified MIT (permissive) · 9dc202f235585e84 · report
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.
sequence_mask in 55 papers
census: 12 implementations from 15 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind int, dtype int64
repository not located ran · our draft was wrong licence of this copy not recorded · 88bf809d1bc9db4c · report fixture: signature length:Tensor/1/int, max_length:NoneType/0/? · returned Tensor · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

3 sibling assemblies for Conditional Variational Autoencoder with Adversarial Learning (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Conditional Variational Autoencoder with Adversarial Learning (graph method: Conditional Variational Autoencoder with Adversarial Learning). 24 bricks; individually on a fixture: 16 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. SynthesizerTrn entry · level 0 · unverified · c21db10c88a81887
  2. Generator model · level 1 · ran · ccc7aa1ec0421795
  3. PosteriorEncoder model · level 0 · unverified · c148debeb5b49924
  4. ResidualCouplingBlock model · level 0 · unverified · 20b53a6e6135c48b
  5. TextEncoder model · level 0 · unverified · 9d5ca7de433e20e7
  6. maximum_path helper · level 0 · unverified · 4f078be04af51043
  7. rand_slice_segments helper · level 1 · ran; the contract check could not run (RAISES) · 0b891bcd5e4b4be1
  8. slice_segments helper · level 1 · ran; the contract check could not run (RAISES) · 5e342f73b3b911ec
  9. spectrogram_torch_data helper · level 1 · ran · our draft was wrong · 08beff5564cff157
  10. ResBlock1 helper · level 1 · ran · 54658cf2627bb592
  11. ResBlock2 helper · level 1 · ran · 054d6a8b9d719923
  12. init_weights helper · level 0 · unverified · b6ab401f5185c8e7
  13. WN helper · level 1 · ran · c95240fe5270874a
  14. sequence_mask helper · level 1 · ran · our draft was wrong · 88bf809d1bc9db4c
  15. Flip helper · level 1 · ran · 1792455895b131d4
  16. ResidualCouplingLayer helper · level 0 · unverified · 60a5c0ef9ff2d916
  17. Encoder helper · level 0 · unverified · 62c7b592b2d2297b
  18. spectrogram_torch helper · level 1 · ran · our draft was wrong · 2a01b8026e5c2bc7
  19. get_padding helper · level 1 · ran · honoured contract · a26f85d7c72ef39a
  20. fused_add_tanh_sigmoid_multiply helper · level 1 · ran; the contract check could not run (RAISES) · b38f9c28c5117398
  21. FFN helper · level 1 · ran · 105de269bbc6a61f
  22. LayerNorm helper · level 1 · ran · 649dfa04ce7522a2
  23. MultiHeadAttention helper · level 1 · ran · 1565e9cf603643df
  24. convert_pad_shape helper · level 1 · ran · honoured contract · 59ae0708b1e8d94b

harvested Assembly for Conditional Variational Autoencoder with Adversarial Learning (graph method: Conditional Variational Autoencoder with Adversarial Learning). 16 bricks; individually on a fixture: 10 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. SynthesizerTrn entry · level 0 · unverified · f0ac43353f543134
  2. Encoder model · level 0 · unverified · 862e2838890719eb
  3. Generator model · level 0 · unverified · b9e59ecadc84c228
  4. ResidualCouplingBlock model · level 0 · unverified · 7f154bf0fb8dcbbb
  5. SpeakerEncoder model · level 1 · ran · b35a311435634a3e
  6. rand_slice_segments helper · level 1 · ran; the contract check could not run (RAISES) · 0b891bcd5e4b4be1
  7. WN helper · level 1 · ran · 0b63f8b32a435c7e
  8. sequence_mask helper · level 1 · ran · our draft was wrong · 88bf809d1bc9db4c
  9. ResBlock1 helper · level 1 · ran · 54658cf2627bb592
  10. ResBlock2 helper · level 1 · ran · 054d6a8b9d719923
  11. init_weights helper · level 0 · unverified · b6ab401f5185c8e7
  12. Flip helper · level 1 · ran · 1792455895b131d4
  13. ResidualCouplingLayer helper · level 0 · unverified · 1541e569125c52bd
  14. slice_segments helper · level 1 · ran; the contract check could not run (RAISES) · 5e342f73b3b911ec
  15. fused_add_tanh_sigmoid_multiply helper · level 1 · ran; the contract check could not run (RAISES) · b38f9c28c5117398
  16. get_padding helper · level 1 · ran · honoured contract · a26f85d7c72ef39a

harvested Assembly for Conditional Variational Autoencoder with Adversarial Learning (graph method: Conditional Variational Autoencoder with Adversarial Learning). 33 bricks; individually on a fixture: 19 ran (of which 9 constructed an object rather than computing a result; 13 with no instrument failure: 2 honoured, 0 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 14 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. SynthesizerTrn entry · level 0 · unverified · c27a865f5e63bc20
  2. DurationPredictor helper · level 1 · ran · d2782997a07f6dfc
  3. Generator model · level 0 · unverified · fa239ec0b64f95b1
  4. PosteriorEncoder model · level 0 · unverified · c148debeb5b49924
  5. ResidualCouplingBlock model · level 0 · unverified · 20b53a6e6135c48b
  6. StochasticDurationPredictor model · level 0 · unverified · 76a16536fc995a46
  7. TextEncoder model · level 0 · unverified · 9d5ca7de433e20e7
  8. generate_path helper · level 1 · ran; the contract check could not run (RAISES) · 6981a5db6f046922
  9. maximum_path helper · level 0 · unverified · 4f078be04af51043
  10. rand_slice_segments helper · level 1 · ran; the contract check could not run (RAISES) · 0b891bcd5e4b4be1
  11. sequence_mask helper · level 1 · ran · our draft was wrong · 88bf809d1bc9db4c
  12. LayerNorm helper · level 1 · ran · 649dfa04ce7522a2
  13. ResBlock1 helper · level 1 · ran · 54658cf2627bb592
  14. ResBlock2 helper · level 1 · ran · 054d6a8b9d719923
  15. init_weights helper · level 0 · unverified · b6ab401f5185c8e7
  16. WN helper · level 1 · ran · c95240fe5270874a
  17. Flip helper · level 1 · ran · 1792455895b131d4
  18. ResidualCouplingLayer helper · level 0 · unverified · 60a5c0ef9ff2d916
  19. ConvFlow helper · level 0 · unverified · 6121d5117e03763b
  20. DDSConv helper · level 1 · ran · f0dbf406caa930d9
  21. ElementwiseAffine helper · level 1 · ran · d6380a9b9627f5fa
  22. Log helper · level 1 · ran · ecedf3198e3c1020
  23. Encoder helper · level 0 · unverified · 62c7b592b2d2297b
  24. convert_pad_shape helper · level 1 · ran · honoured contract · 59ae0708b1e8d94b
  25. slice_segments helper · level 1 · ran; the contract check could not run (RAISES) · 5e342f73b3b911ec
  26. get_padding helper · level 1 · ran · honoured contract · a26f85d7c72ef39a
  27. fused_add_tanh_sigmoid_multiply helper · level 1 · ran; the contract check could not run (RAISES) · b38f9c28c5117398
  28. piecewise_rational_quadratic_transform helper · level 0 · unverified · 8e2e7c27501567b6
  29. FFN helper · level 1 · ran · 105de269bbc6a61f
  30. MultiHeadAttention helper · level 1 · ran · 1565e9cf603643df
  31. rational_quadratic_spline helper · level 0 · unverified · b4db05cf916b9553
  32. unconstrained_rational_quadratic_spline helper · level 1 · ran · our draft was wrong · 9e31572da16d9de4
  33. searchsorted helper · level 0 · unverified · e85d747983c4f5d8

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2106.06103") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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