SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2011.00316 · 2020

AGAIN-VC: A One-shot Voice Conversion using Activation Guidance and Adaptive Instance Normalization

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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; 1 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures of our instrument; 0 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/2011.00316.json · badge: /api/ran/2011.00316.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
KimythAnly/AGAIN-VC canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
count_parameters Ran
ran, honoured the contract we drafted
KimythAnly/AGAIN-VC/model/again.py
code served (permissive licence) · get_code("f6b944f50d3f15ae")
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) and returned int, ndim 0, dtype family int, shape () 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 torch
import torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

ARGS = {
    "model": model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () 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
gen_wav_list Ran
ran on a synthesized input
KimythAnly/AGAIN-VC/agent/inferencer.py
code served (permissive licence) · get_code("6a319eaf83ff430a")
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 list, ndim 1, 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 os
import tempfile
import shutil

# Create a temporary directory with a .wav file for testing
temp_dir = tempfile.mkdtemp()
wav_file_path = os.path.join(temp_dir, "test_audio.wav")

# Create a dummy .wav file
with open(wav_file_path, 'wb') as f:
    f.write(b'RIFF' + b'\x00' * 36 + b'WAVE')

# Test with directory path
ARGS = {
    'path': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
preprocess_one Ran
ran on a synthesized input
KimythAnly/AGAIN-VC/preprocessor/base.py
code served (permissive licence) · get_code("6130fb54ce52b092")
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 1, dtype family float, shape (16000,) 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 os
import logging
import numpy as np
import torch
import torch.nn as nn

torch.manual_seed(0)
logging.basicConfig(level=logging.WARNING)

# Create a minimal config class
class MinimalConfig:
    def __init__(self, dtype='wav'):
        self.dtype = dtype
        self.sample_rate = 16000

# Create a minimal module that implements the required methods
class MinimalModule(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.config = config
    
    def load_wav(self, input_path):
        # Return a dummy waveform (1D numpy array)
        return np.random.randn(16000).astype(np.float32)
    
    def wav2mel(self, y):
        # Return a dummy melspectrogram (2D numpy array)
        return np.random.randn(128, 100).astype(np.float32)
    
    def wav2s3prl_spec(self, y):
        # Return a dummy s3prl spectrogram
        return np.random.randn(256, 100).astype(np.float32)
    
    def wav2resemblyzer(self, y):
        # Return a dummy resemblyzer embedding
        return np.random.randn(256).astype(np.float32)

# Create test arguments
config = MinimalConfig(dtype='wav')
module = MinimalModule(config)
input_items = ('dummy_audio.wav', 'test_audio')
output_path = ''

ARGS = {
    'input_items': input_items,
    'module': module,
    'output_path': output_path,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (16000,) — shape (16000,) 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
train_step Ran
ran on a synthesized input
KimythAnly/AGAIN-VC/model/again.py
code served (permissive licence) · get_code("37bab301d0d6a8f0")
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 dict. 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)

class SimpleAutoencoder(nn.Module):
    def __init__(self, input_dim=4, hidden_dim=8):
        super().__init__()
        self.encoder = nn.Linear(input_dim, hidden_dim)
        self.decoder = nn.Linear(hidden_dim, input_dim)
    
    def forward(self, x):
        # x shape: (batch, seq_len, input_dim) or (batch, input_dim)
        # Flatten if needed for linear layer
        original_shape = x.shape
        if len(x.shape) == 3:
            batch, seq, dim = x.shape
            x_flat = x.reshape(-1, dim)
            encoded = self.encoder(x_flat)
            decoded = self.decoder(encoded)
            return decoded.reshape(original_shape)
        else:
            encoded = self.encoder(x)
            decoded = self.decoder(encoded)
            return decoded
    
    def inference(self, content, style):
        # Simple inference: just pass through decoder
        return self.decoder(self.encoder(content))

model = SimpleAutoencoder(input_dim=4, hidden_dim=8)
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
criterion_l1 = nn.L1Loss()
device = torch.device('cpu')

model_state = {
    'model': model,
    'optimizer': optimizer,
    'criterion_l1': criterion_l1,
    'device': device,
    'grad_norm': 1.0
}

data = {
    'mel': torch.randn(2, 3, 4)
}

ARGS = {
    'model_state': model_state,
    'data': data,
    'train': True
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 3 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
count_parameters 180 other papers
29 dated earlier, 151 later · 8 only as an assembly brick
1705.08415 (2017-05)
Supervised Community Detection with Line Graph Neural Networks
1707.01926 (2017-07)
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
1808.09367 (2018-08)
Deriving Machine Attention from Human Rationales
and 177 more not named here

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

Recently, voice conversion (VC) has been widely studied. Many VC systems use disentangle-based learning techniques to separate the speaker and the linguistic content information from a speech signal. Subsequently, they convert the voice by changing the speaker information to that of the target speaker. To prevent the speaker information from leaking into the content embeddings, previous works either reduce the dimension or quantize the content embedding as a strong information bottleneck. These mechanisms somehow hurt the synthesis quality. In this work, we propose AGAIN-VC, an innovative VC system using Activation Guidance and Adaptive Instance Normalization. AGAIN-VC is an auto-encoder-based model, comprising of a single encoder and a decoder. With a proper activation as an information bottleneck on content embeddings, the trade-off between the synthesis quality and the speaker similarity of the converted speech is improved drastically. This one-shot VC system obtains the best performance regardless of the subjective or objective evaluations.

For agents

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

get_harvested_code_for_paper("2011.00316")
get_code_for_paper("2011.00316")
have("2011.00316")

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

curl https://syntology.ai/api/ran/2011.00316.json

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

[![Syntology run record](https://syntology.ai/api/ran/2011.00316.svg)](https://syntology.ai/paper/2011.00316)

Connect an agent — have() is free.