SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1904.04472 · 2019

Probability density distillation with generative adversarial networks for high-quality parallel waveform generation

arXiv · PDF · Open in the Atlas

Code that ran

3 of 14 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures of our instrument; 11 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1904.04472.json · badge: /api/ran/1904.04472.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
markliou/model_distillation community (classifier label)
classifier basis not recorded on the link
3 ran · 11 no recorded run
FunctionStatusWhere it lives
generate_perlin_noise_2d Ran
ran on a synthesized input
markliou/model_distillation/mnist_distillation_ad.py
code served (permissive licence) · get_code("b6291ef085200c5d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (64, 64) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Set random seed for reproducibility
np.random.seed(0)

# Define arguments for generate_perlin_noise_2d
# shape: output shape (height, width) of the generated noise
# res: resolution of the gradient grid (height, width)
ARGS = {
    "shape": (64, 64),
    "res": (8, 8)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (64, 64) — shape (64, 64) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
generate_perlin_noise_2d Ran
ran on a synthesized input
markliou/model_distillation/mnist_distillation_gumbel.py
code served (permissive licence) · get_code("6ff0c89bc6b1b7de")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (64, 64) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Set random seed for reproducibility
np.random.seed(0)

# Define arguments for generate_perlin_noise_2d
# shape: tuple of (height, width) for output noise dimensions
# res: tuple of (height, width) for resolution/grid dimensions
ARGS = {
    'shape': (64, 64),
    'res': (8, 8)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (64, 64) — shape (64, 64) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
generate_perlin_noise_2d Ran
ran on a synthesized input
markliou/model_distillation/mnist_distillation_perlin_BTF.py
code served (permissive licence) · get_code("bf2e08b9b2e1ae9d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (64, 48) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Set random seed for reproducibility
np.random.seed(0)

# Define arguments for generate_perlin_noise_2d
# shape: tuple of (height, width) for the output noise grid
# res: tuple of (height, width) for the resolution/grid size

shape = (64, 48)  # Output grid dimensions (distinct sizes for clarity)
res = (8, 6)      # Resolution grid dimensions (must divide shape evenly)

ARGS = {
    "shape": shape,
    "res": res
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (64, 48) — shape (64, 48) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv_net Not yet run
unverified (harvested, no recorded run)
markliou/model_distillation/mnist_distillation.py
code served (permissive licence) · get_code("315e181a80930c67")
How it ran

no invocation recorded.

conv_net Not yet run
unverified (harvested, no recorded run)
markliou/model_distillation/mnist_distillation_ad.py
code served (permissive licence) · get_code("3d0901d6d44dabc7")
How it ran

no invocation recorded.

conv_net Not yet run
unverified (harvested, no recorded run)
markliou/model_distillation/mnist_distillation_ad_check.py
code served (permissive licence) · get_code("b61b2e1085ff3682")
How it ran

no invocation recorded.

noise_gen Not yet run
unverified (harvested, no recorded run)
markliou/model_distillation/mnist_distillation_REINFORCE.py
code served (permissive licence) · get_code("acd3e548b25eeab6")
How it ran

no invocation recorded.

noise_gen Not yet run
unverified (harvested, no recorded run)
markliou/model_distillation/mnist_distillation_ad.py
code served (permissive licence) · get_code("130191025c0ec547")
How it ran

no invocation recorded.

noise_gen Not yet run
unverified (harvested, no recorded run)
markliou/model_distillation/mnist_distillation_ad_3.py
code served (permissive licence) · get_code("50d2b78eaed6fe80")
How it ran

no invocation recorded.

noise_gen Not yet run
unverified (harvested, no recorded run)
markliou/model_distillation/mnist_distillation_ad_4.py
code served (permissive licence) · get_code("2f6855c811935d20")
How it ran

no invocation recorded.

noise_gen Not yet run
unverified (harvested, no recorded run)
markliou/model_distillation/mnist_distillation_ad_check.py
code served (permissive licence) · get_code("ef5bf77dc882568c")
How it ran

no invocation recorded.

qconv_net Not yet run
unverified (harvested, no recorded run)
markliou/model_distillation/mnist_distillation.py
code served (permissive licence) · get_code("384c197c7d5032b7")
How it ran

no invocation recorded.

qconv_net Not yet run
unverified (harvested, no recorded run)
markliou/model_distillation/mnist_distillation_gumbel.py
code served (permissive licence) · get_code("43ec22c688c8fa7f")
How it ran

no invocation recorded.

qconv_net Not yet run
unverified (harvested, no recorded run)
markliou/model_distillation/mnist_distillation_perlin_BTF.py
code served (permissive licence) · get_code("2e3e963a34a01132")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 13 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

This paper proposes an effective probability density distillation (PDD) algorithm for WaveNet-based parallel waveform generation (PWG) systems. Recently proposed teacher-student frameworks in the PWG system have successfully achieved a real-time generation of speech signals. However, the difficulties optimizing the PDD criteria without auxiliary losses result in quality degradation of synthesized speech. To generate more natural speech signals within the teacher-student framework, we propose a novel optimization criterion based on generative adversarial networks (GANs). In the proposed method, the inverse autoregressive flow-based student model is incorporated as a generator in the GAN framework, and jointly optimized by the PDD mechanism with the proposed adversarial learning method. As this process encourages the student to model the distribution of realistic speech waveform, the perceptual quality of the synthesized speech becomes much more natural. Our experimental results verify that the PWG systems with the proposed method outperform both those using conventional approaches, and also autoregressive generation systems with a well-trained teacher WaveNet.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1904.04472")
get_code_for_paper("1904.04472")
have("1904.04472")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1904.04472.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1904.04472.svg)](https://syntology.ai/paper/1904.04472)

Connect an agent — have() is free.