SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.14513 · NeurIPS · 2021

Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations

Hyeong-Seok Choi, Kyogu Lee, Juheon Lee, Wansoo Kim, Jie Lee, Hoon Heo, Gsai, Aiis

arXiv · PDF · Open in the Atlas

Code that ran

8 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (7 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 8 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2110.14513.json · badge: /api/ran/2110.14513.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
dhchoi99/NANSY community
Papers with Code archive
5 ran · 2 no recorded run
revsic/torch-nansy community
Papers with Code archive
3 ran · 0 no recorded run
FunctionStatusWhere it lives
ConditionalLayerNorm Ran
ran on a synthesized input
revsic/torch-nansy/nansy/synthesizer.py
code served (permissive licence) · get_code("f9343c6bc90f8cd4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 torch
import torch.nn as nn

class ConditionalLayerNorm(nn.Module):
    """Conditional layer normalization.
    """

    def __init__(self, spk: int, channels: int):
        """Initializer.
        Args:
            spk: size of the speaker emebddings.
            chanensl: size of the input channels.
        """
        super().__init__()
        self.norm = nn.InstanceNorm1d(channels, affine=False)
        self.proj = nn.Linear(spk, channels * 2)

    def forward(self, inputs: torch.Tensor, spk: torch.Tensor) -> torch.Tensor:
        """Whintening and colorizing the inputs adaptively.
        Args:
            inputs: [torch.float32; [B, C, T]], input tensor.
            spk: [torch.float32; [B, S]], speaker embedding.
                where C = `channels`, S = `spk`.
        """
        scale, bias = self.proj(spk).chunk(2, dim=1)
        return self.norm(inputs) * scale[..., None] + bias[..., None]


INIT_ARGS = {
    "spk": 5,
    "channels": 4,
}

ARGS = {
    "inputs": torch.randn(2, 4, 3),
    "spk": torch.randn(2, 5),
}

if __name__ == "__main__":
    model = ConditionalLayerNorm(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Output: {output}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
ConditionalLayerNorm Ran
ran on a synthesized input · constructed an object; no result was computed
dhchoi99/NANSY/models/synthesis.py
pointer only (licence: NONE) · get_code("544e239a538d061c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dhchoi99/NANSY when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ConvGLU Ran
ran on a synthesized input · constructed an object; no result was computed
revsic/torch-nansy/nansy/synthesizer.py
code served (permissive licence) · get_code("04c8057fc6f2deff")
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 an instance of its own class, ConvGLU: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Parameters for ConvGLU
channels = 8
dropout = 0.1
kernels = 3
dilation = 1
blocks = 2
spk = 5  # speaker embedding size

ARGS = {
    "channels": channels,
    "dropout": dropout,
    "kernels": kernels,
    "dilation": dilation,
    "blocks": blocks,
    "spk": spk,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ConvGLU — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ConvGLU output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
ConvGLU Ran
ran on a synthesized input · constructed an object; no result was computed
dhchoi99/NANSY/models/synthesis.py
pointer only (licence: NONE) · get_code("af41e4f52f661656")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dhchoi99/NANSY when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

PreConv Ran
ran on a synthesized input · constructed an object; no result was computed
dhchoi99/NANSY/models/synthesis.py
pointer only (licence: NONE) · get_code("e9e0b2afcfc28781")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dhchoi99/NANSY when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ResBlock1 Ran
ran on a synthesized input · constructed an object; no result was computed
dhchoi99/NANSY/models/synthesis.py
pointer only (licence: NONE) · get_code("a2ce4f0df0596d33")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dhchoi99/NANSY when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ResBlock2 Ran
ran on a synthesized input · constructed an object; no result was computed
dhchoi99/NANSY/models/synthesis.py
pointer only (licence: NONE) · get_code("2330fc6e8150cf5e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dhchoi99/NANSY when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Synthesizer Ran
ran on a synthesized input · constructed an object; no result was computed
revsic/torch-nansy/nansy/synthesizer.py
code served (permissive licence) · get_code("d2d2661a86323397")
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 an instance of its own class, Synthesizer: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Define the ARGS dictionary with all parameters for Synthesizer
ARGS = {
    'in_channels': 13,
    'out_channels': 1,
    'channels': 8,
    'spk': 4,
    'kernels': 3,
    'dilation': 2,
    'leak': 0.1,
    'dropout': 0.1,
    'preconv_blocks': 1,
    'preblocks': [2],
    'postblocks': [2],
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Synthesizer — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Synthesizer output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
Generator Not yet run
unverified (harvested, no recorded run)
dhchoi99/NANSY/models/synthesis.py
pointer only (licence: NONE) · get_code("aedea83432badf8d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dhchoi99/NANSY when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Synthesis Not yet run
unverified (harvested, no recorded run)
dhchoi99/NANSY/models/synthesis.py
pointer only (licence: NONE) · get_code("2c98d43d678e4da1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dhchoi99/NANSY when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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.

FunctionAlso present inEarliest-datedOthers named
ResBlock1
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2010.05646 (2020-10)
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
ResBlock2
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2010.05646 (2020-10)
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

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 2026-11-22.

Repositories linked to this paper

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

Abstract

We present a neural analysis and synthesis (NANSY) framework that can manipulate voice, pitch, and speed of an arbitrary speech signal. Most of the previous works have focused on using information bottleneck to disentangle analysis features for controllable synthesis, which usually results in poor reconstruction quality. We address this issue by proposing a novel training strategy based on information perturbation. The idea is to perturb information in the original input signal (e.g., formant, pitch, and frequency response), thereby letting synthesis networks selectively take essential attributes to reconstruct the input signal. Because NANSY does not need any bottleneck structures, it enjoys both high reconstruction quality and controllability. Furthermore, NANSY does not require any labels associated with speech data such as text and speaker information, but rather uses a new set of analysis features, i.e., wav2vec feature and newly proposed pitch feature, Yingram, which allows for fully self-supervised training. Taking advantage of fully selfsupervised training, NANSY can be easily extended to a multilingual setting by simply training it with a multilingual dataset. The experiments show that NANSY can achieve significant improvement in performance in several applications such as zero-shot voice conversion, pitch shift, and time-scale modification 1 .

For agents

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

get_harvested_code_for_paper("2110.14513")
get_code_for_paper("2110.14513")
have("2110.14513")

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

curl https://syntology.ai/api/ran/2110.14513.json

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

[![Syntology run record](https://syntology.ai/api/ran/2110.14513.svg)](https://syntology.ai/paper/2110.14513)

Connect an agent — have() is free.