SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.11284 · 2020

Unsupervised Speech Decomposition via Triple Information Bottleneck

arXiv · PDF · Open in the Atlas

Code that ran

8 of 12 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 8 have no contract verdict; 0 failures of our instrument; 4 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/2004.11284.json · badge: /api/ran/2004.11284.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
auspicious3000/SpeechSplit canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
CODEJIN/SPEECHSPLIT community (classifier label)
classifier basis not recorded on the link
4 ran · 1 no recorded run
auspicious3000/autovc community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
tobwei/disentintel community (classifier label)
classifier basis not recorded on the link
0 ran · 1 no recorded run
FunctionStatusWhere it lives
Preemphasis Ran
ran on a synthesized input
CODEJIN/SPEECHSPLIT/Audio.py
code served (permissive licence) · get_code("494d58dba436fa48")
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 (6,) 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 numpy as np
from scipy import signal

torch.manual_seed(0)

# The function takes audio and pre_emphasis as parameters
# audio should be array-like (numpy array or list) that can be passed to signal.lfilter
# pre_emphasis is a float with default 0.97

# Create a small audio array
audio = np.array([0.1, 0.2, 0.3, 0.4, 0.5, 0.6], dtype=np.float32)

# Define the arguments dictionary
ARGS = {
    "audio": audio,
    "pre_emphasis": 0.97
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, 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 (6,) — shape (6,) 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
butter_highpass Ran
ran on a synthesized input
auspicious3000/SpeechSplit/utils.py
code served (permissive licence) · get_code("bd4055b8505914e7")
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 tuple, ndim 2, 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.

from scipy import signal

ARGS = {
    'cutoff': 1000,
    'fs': 44100,
    'order': 5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — a tuple 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
cumulativeMeanNormalizedDifferenceFunction Ran
ran on a synthesized input
CODEJIN/SPEECHSPLIT/yin.py
code served (permissive licence) · get_code("e507922638a3a56e")
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 (6,) 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

# Create a small difference function array
# The function expects df to be an array-like object with numerical values
# N represents the length of the original data
df = np.array([1.0, 0.8, 0.6, 0.5, 0.4, 0.3])
N = len(df)

ARGS = {
    "df": df,
    "N": N
}
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 1, dtype family float, shape (6,) — shape (6,) 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
differenceFunction Ran
ran on a synthesized input
CODEJIN/SPEECHSPLIT/yin.py
code served (permissive licence) · get_code("3cbbf9560f72cc60")
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 (4,) 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

# Construct arguments for differenceFunction
# The function expects:
# - x: audio data (array-like)
# - N: length of data (int)
# - tau_max: integration window size (int)

# Create small audio data
audio_data = np.array([0.1, 0.2, 0.15, 0.3, 0.25, 0.1, 0.05, 0.2], dtype=np.float64)
N = len(audio_data)
tau_max = 4

ARGS = {
    "x": audio_data,
    "N": N,
    "tau_max": tau_max
}
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 1, dtype family float, shape (4,) — shape (4,) 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
getPitch Ran
ran on a synthesized input
CODEJIN/SPEECHSPLIT/yin.py
code served (permissive licence) · get_code("762aa23bfe00152c")
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 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 numpy as np

torch.manual_seed(0)

# The function expects:
# - cmdf: array-like object that supports indexing with integers
# - tau_min: integer (minimum period)
# - tau_max: integer (maximum period)
# - harmo_th: float (threshold, default 0.1)

# Create a small CMDF array (Cumulative Mean Normalized Difference function)
# It needs to be indexable and contain float values
# We'll create an array with some values below and above the threshold
cmdf_values = np.array([
    0.5,   # tau=0
    0.15,  # tau=1 (below threshold of 0.1? No, above)
    0.08,  # tau=2 (below threshold)
    0.07,  # tau=3 (below threshold, and below previous)
    0.09,  # tau=4 (above previous, so loop would stop)
    0.2,   # tau=5
    0.3,   # tau=6
    0.4,   # tau=7
    0.5,   # tau=8
], dtype=np.float32)

tau_min = 1
tau_max = 8
harmo_th = 0.1

ARGS = {
    "cmdf": cmdf_values,
    "tau_min": tau_min,
    "tau_max": tau_max,
    "harmo_th": harmo_th
}
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 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
get_loader Ran
ran on a synthesized input
auspicious3000/SpeechSplit/data_loader.py
code served (permissive licence) · get_code("60e1b14d63143cce")
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 DataLoader. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-27T00:55:05Z. 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 numpy as np
import os
import tempfile
import pickle

torch.manual_seed(0)
np.random.seed(0)

# Create temporary directories for the dataset
temp_root = tempfile.mkdtemp()
temp_feat = tempfile.mkdtemp()

# Create mock train.pkl with metadata
# Each entry: [spk_id, embedding, path_to_npy_file]
mock_meta = [
    [0, np.random.randn(256).astype(np.float32), 'sample_0.npy'],
    [1, np.random.randn(256).astype(np.float32), 'sample_1.npy'],
]

with open(os.path.join(temp_root, 'train.pkl'), 'wb') as f:
    pickle.dump(mock_meta, f)

# Create mock .npy files for spectral and F0 features
for i, (spk_id, emb, fname) in enumerate(mock_meta):
    # Create spectral features: shape (100, 80) - time x mel-bins
    sp_data = np.random.rand(100, 80).astype(np.float32)
    np.save(os.path.join(temp_root, fname), sp_data)
    
    # Create F0 features: shape (100,) - time dimension
    f0_data = np.random.rand(100).astype(np.float32)
    np.save(os.path.join(temp_feat, fname), f0_data)

# Create a simple hparams config class
class HParams:
    def __init__(self):
        self.root_dir = temp_root
        self.feat_dir = temp_feat
        self.mode = 'train'
        self.min_len_seq = 20
        self.max_len_seq = 50
        self.max_len_pad = 60
        self.batch_size = 2
        self.samplier = 2  # Note: typo in original function
        self.shuffle = False
        self.num_workers = 0

hparams = HParams()

ARGS = {
    'hparams': hparams
}
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 DataLoader — a DataLoader output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataLoader output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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
get_loader Ran
ran on a synthesized input
auspicious3000/autovc/data_loader.py
code served (permissive licence) · get_code("9190dd81722f0209")
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 DataLoader. 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 numpy as np
import pickle
import os
import tempfile
from torch.utils import data

torch.manual_seed(0)
np.random.seed(0)

# Create a temporary directory with mock data
temp_dir = tempfile.mkdtemp()

# Create mock train.pkl file
# Structure: list of speakers, each speaker is a list where:
# - [0] is speaker name (string)
# - [1] is embedding (numpy array)
# - [2+] are paths to utterance files
mock_meta = [
    ["speaker_0", np.random.randn(128).astype(np.float32), "utt_0_0.npy", "utt_0_1.npy"],
    ["speaker_1", np.random.randn(128).astype(np.float32), "utt_1_0.npy", "utt_1_1.npy"],
]

# Save pickle file
pickle.dump(mock_meta, open(os.path.join(temp_dir, 'train.pkl'), 'wb'))

# Create mock utterance npy files
for i in range(2):
    for j in range(2):
        utt_data = np.random.randn(np.random.randint(100, 150), 13).astype(np.float32)
        np.save(os.path.join(temp_dir, f"utt_{i}_{j}.npy"), utt_data)

ARGS = {
    "root_dir": temp_dir,
    "batch_size": 2,
    "len_crop": 128,
    "num_workers": 0,
}
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 DataLoader — a DataLoader output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataLoader 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
speaker_normalization Ran
ran on a synthesized input
auspicious3000/SpeechSplit/utils.py
code served (permissive licence) · get_code("3c696d6a48af79fc")
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; no output shape is stated. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-27T00:55:05Z. 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 numpy as np

# Create a small f0 array with some values
f0 = np.array([0.0, 100.0, 150.0, 0.0, 120.0], dtype=np.float32)

# Create index_nonzero - indices where f0 is nonzero
index_nonzero = np.array([1, 2, 4], dtype=np.int32)

# Create mean and std for normalization
mean_f0 = 100.0
std_f0 = 25.0

ARGS = {
    "f0": f0,
    "index_nonzero": index_nonzero,
    "mean_f0": mean_f0,
    "std_f0": std_f0,
}
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 1, dtype family float — no output shape is stated: no later run recorded an output shape for this sample (observed_output and metamorphic_properties carry none; shape_contract and output_contract record ndim only)
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 syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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
get_loader Not yet run
unverified (harvested, no recorded run)
tobwei/disentintel/data_loader.py
code served (permissive licence) · get_code("a06b32f0a03e5e15")
How it ran

no invocation recorded.

parse_values Not yet run
unverified (harvested, no recorded run)
auspicious3000/SpeechSplit/tfcompat/hparam.py
code served (permissive licence) · get_code("a526fa3bf263b12d")
How it ran

no invocation recorded.

pySTFT Not yet run
unverified (harvested, no recorded run)
auspicious3000/SpeechSplit/utils.py
code served (permissive licence) · get_code("d02424cc0a1be609")
How it ran

no invocation recorded.

random_resmpling_factors Not yet run
unverified (harvested, no recorded run)
CODEJIN/SPEECHSPLIT/Datasets.py
code served (permissive licence) · get_code("a2f543b45bd3fb47")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 7 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
Preemphasis 1 other paper
1 later
2009.01776 (2020-09)
HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis
cumulativeMeanNormalizedDifferenceFunction 1 other paper
1 later
2009.01776 (2020-09)
HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis
differenceFunction 1 other paper
1 later
2009.01776 (2020-09)
HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis
getPitch 1 other paper
1 later
2009.01776 (2020-09)
HiFiSinger: Towards High-Fidelity Neural Singing Voice 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

Speech information can be roughly decomposed into four components: language content, timbre, pitch, and rhythm. Obtaining disentangled representations of these components is useful in many speech analysis and generation applications. Recently, state-of-the-art voice conversion systems have led to speech representations that can disentangle speaker-dependent and independent information. However, these systems can only disentangle timbre, while information about pitch, rhythm and content is still mixed together. Further disentangling the remaining speech components is an under-determined problem in the absence of explicit annotations for each component, which are difficult and expensive to obtain. In this paper, we propose SpeechSplit, which can blindly decompose speech into its four components by introducing three carefully designed information bottlenecks. SpeechSplit is among the first algorithms that can separately perform style transfer on timbre, pitch and rhythm without text labels. Our code is publicly available at https://github.com/auspicious3000/SpeechSplit.

For agents

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

get_harvested_code_for_paper("2004.11284")
get_code_for_paper("2004.11284")
have("2004.11284")

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

curl https://syntology.ai/api/ran/2004.11284.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.11284.svg)](https://syntology.ai/paper/2004.11284)

Connect an agent — have() is free.