SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.02250 · 2024

Multi-Stage Speech Bandwidth Extension with Flexible Sampling Rate Control

arXiv · PDF · Open in the Atlas

Code that ran

14 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 12 failures of our instrument; 0 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2406.02250.json · badge: /api/ran/2406.02250.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
yxlu-0102/AP-BWE canonical (classifier label)
classifier basis: plan_row
14 ran · 0 no recorded run
FunctionStatusWhere it lives
load_checkpoint Ran
ran; our contract draft was wrong, not the code
yxlu-0102/AP-BWE/inference/inference_16k.py
code served (permissive licence) · get_code("1644a2f2942ffe4c")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned dict. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T22:41:19Z). 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 os
import torch
import tempfile

torch.manual_seed(0)

# Create a temporary checkpoint file
with tempfile.NamedTemporaryFile(mode='wb', delete=False, suffix='.pt') as f:
    temp_filepath = f.name
    # Create a simple checkpoint dict and save it
    checkpoint_data = {
        'model_state': torch.randn(2, 4),
        'optimizer_state': torch.randn(3, 5),
        'epoch': 10
    }
    torch.save(checkpoint_data, temp_filepath)

ARGS = {
    'filepath': temp_filepath,
    'device': torch.device('cpu')
}
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 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
amp_pha_istft Ran
ran; our contract draft was wrong, not the code
yxlu-0102/AP-BWE/datasets/dataset.py
code served (permissive licence) · get_code("f733b33d89d50732")
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 Tensor, ndim 2, dtype family float, shape (2, 16) 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)

# The function expects:
# - log_amp: a tensor of log amplitudes (STFT magnitudes in log scale)
# - pha: a tensor of phases
# - n_fft: integer, FFT size
# - hop_size: integer, hop length
# - win_size: integer, window size
# - center: boolean, whether to center-pad the input

# For istft to work, the frequency dimension must be n_fft // 2 + 1
# Let's create minimal valid tensors

n_fft = 16
hop_size = 4
win_size = 16

# istft expects input of shape (..., freq_bins, time_frames)
# where freq_bins = n_fft // 2 + 1 = 9
freq_bins = n_fft // 2 + 1
time_frames = 5

# Create log amplitude and phase tensors
log_amp = torch.randn(2, freq_bins, time_frames)  # batch_size=2, freq=9, time=5
pha = torch.randn(2, freq_bins, time_frames)  # same shape

ARGS = {
    "log_amp": log_amp,
    "pha": pha,
    "n_fft": n_fft,
    "hop_size": hop_size,
    "win_size": win_size,
    "center": 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 Tensor, ndim 2, dtype family float, shape (2, 16) — shape (2, 16) 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
amp_pha_stft Ran
ran; our contract draft was wrong, not the code
yxlu-0102/AP-BWE/datasets/dataset.py
code served (permissive licence) · get_code("d5882ead8f1fcfd3")
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. 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

torch.manual_seed(0)

# Construct arguments for amp_pha_stft
audio = torch.randn(2, 16000)  # batch_size=2, audio_length=16000
n_fft = 1024
hop_size = 512
win_size = 1024
center = True

ARGS = {
    "audio": audio,
    "n_fft": n_fft,
    "hop_size": hop_size,
    "win_size": win_size,
    "center": center,
}
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 tuple — a tuple output has no array shape of its own; none is 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
cal_lsd Ran
ran; our contract draft was wrong, not the code
yxlu-0102/AP-BWE/cal_metrics.py
code served (permissive licence) · get_code("32a2dab9f5829d6a")
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 Tensor, ndim 0, dtype family float, 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
torch.manual_seed(0)

# Create small audio tensors for pred and target
# Audio tensors should be 1D for the stft function
# Let's create batch of 2 audio samples, each with length 4096 (enough for STFT)
batch_size = 2
audio_length = 4096

pred = torch.randn(batch_size, audio_length)
target = torch.randn(batch_size, audio_length)

ARGS = {
    'pred': pred,
    'target': target,
}
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 Tensor, ndim 0, dtype family float, 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
cal_snr Ran
ran; our contract draft was wrong, not the code
yxlu-0102/AP-BWE/cal_metrics.py
code served (permissive licence) · get_code("f17ce5f96671f0c2")
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 Tensor, ndim 0, dtype family float, 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

torch.manual_seed(0)

# Create small test tensors
# The function expects tensors with a last dimension to reduce over
# pred and target should have compatible shapes for subtraction and norm computation
batch_size = 2
feature_dim = 4

pred = torch.randn(batch_size, feature_dim)
target = torch.randn(batch_size, feature_dim)

ARGS = {
    "pred": pred,
    "target": target,
}
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 Tensor, ndim 0, dtype family float, 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
discriminator_loss Ran
ran; our contract draft was wrong, not the code
yxlu-0102/AP-BWE/models/model.py
code served (permissive licence) · get_code("d5fcfe68d25672ba")
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. 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

torch.manual_seed(0)

# The function expects:
# - disc_real_outputs: an iterable of tensors (real discriminator outputs)
# - disc_generated_outputs: an iterable of tensors (generated discriminator outputs)
# Both are zipped together, so they should have the same length

# Create small tensors for discriminator outputs
# These represent discriminator scores for real and generated samples
batch_size = 2
num_outputs = 3  # number of discriminator output layers/scales

disc_real_outputs = [
    torch.randn(batch_size, 4),
    torch.randn(batch_size, 3),
    torch.randn(batch_size, 2),
]

disc_generated_outputs = [
    torch.randn(batch_size, 4),
    torch.randn(batch_size, 3),
    torch.randn(batch_size, 2),
]

ARGS = {
    "disc_real_outputs": disc_real_outputs,
    "disc_generated_outputs": disc_generated_outputs,
}
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 tuple — a tuple output has no array shape of its own; none is 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
feature_loss Ran
ran, honoured the contract we drafted
yxlu-0102/AP-BWE/models/model.py
code served (permissive licence) · get_code("4518cce23c4f900e")
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 Tensor, ndim 0, dtype family float, 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

torch.manual_seed(0)

# Analyzing the function:
# - fmap_r and fmap_g are both iterated over with zip
# - Each element (dr, dg) is iterated over with zip
# - Each element (rl, gl) is used in torch.mean(torch.abs(rl - gl))
# - This means rl and gl should be tensors that support subtraction and abs

# So the structure is:
# fmap_r: list of lists of tensors
# fmap_g: list of lists of tensors

# Create nested lists of feature maps (discriminator outputs)
# Each feature map is a small tensor
fmap_r = [
    [torch.randn(2, 4), torch.randn(2, 3)],  # Two feature maps from first layer
    [torch.randn(2, 5), torch.randn(2, 4)]   # Two feature maps from second layer
]

fmap_g = [
    [torch.randn(2, 4), torch.randn(2, 3)],  # Two feature maps from first layer
    [torch.randn(2, 5), torch.randn(2, 4)]   # Two feature maps from second layer
]

ARGS = {
    "fmap_r": fmap_r,
    "fmap_g": fmap_g
}
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 Tensor, ndim 0, dtype family float, 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
generator_loss Ran
ran; our contract draft was wrong, not the code
yxlu-0102/AP-BWE/models/model.py
code served (permissive licence) · get_code("4e932c6bbfa11b92")
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. 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

torch.manual_seed(0)

# The function expects disc_outputs to be an iterable of tensors
# Each tensor is used with torch.mean and torch.clamp operations
# We'll create a list of small discriminator output tensors

disc_outputs = [
    torch.randn(2, 4),  # Batch of 2, dimension 4
    torch.randn(2, 4),  # Another batch of discriminator outputs
]

ARGS = {
    "disc_outputs": disc_outputs,
}
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 tuple — a tuple output has no array shape of its own; none is 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
get_dataset_filelist Ran
ran; our contract draft was wrong, not the code
yxlu-0102/AP-BWE/datasets/dataset.py
code served (permissive licence) · get_code("c8e0c267926f67c8")
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. 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 tempfile
import os

# Create temporary files with the expected format
temp_dir = tempfile.mkdtemp()
training_file = os.path.join(temp_dir, 'training.txt')
validation_file = os.path.join(temp_dir, 'validation.txt')

# Write training file with pipe-separated format
with open(training_file, 'w', encoding='utf-8') as f:
    f.write("train_001|some_data_1\n")
    f.write("train_002|some_data_2\n")
    f.write("train_003|some_data_3\n")

# Write validation file with pipe-separated format
with open(validation_file, 'w', encoding='utf-8') as f:
    f.write("val_001|some_data_1\n")
    f.write("val_002|some_data_2\n")

# Create a minimal config object with required attributes
class Config:
    def __init__(self, training_path, validation_path):
        self.input_training_file = training_path
        self.input_validation_file = validation_path

config = Config(training_file, validation_file)

ARGS = {
    'a': config
}
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 tuple — a tuple output has no array shape of its own; none is 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
get_padding Ran
ran, honoured the contract we drafted
yxlu-0102/AP-BWE/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from isletennos/mmvc_trainer, is pointer only (licence: NONE) · get_code("a26f85d7c72ef39a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from isletennos/mmvc_trainer, and GitHub detected no licence in that repository 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.

get_padding_2d Ran
ran; our contract draft was wrong, not the code
yxlu-0102/AP-BWE/utils.py
code served (permissive licence) · get_code("4d00da8ae6eb3bed")
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 1, dtype family int; 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 numpy as np

torch.manual_seed(0)

ARGS = {
    'kernel_size': (3, 5),
    'dilation': (1, 2)
}
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 tuple, ndim 1, dtype family int — 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
plot_spectrogram Ran
ran; our contract draft was wrong, not the code
yxlu-0102/AP-BWE/utils.py
code served (permissive licence) · get_code("fea9c37e82071835")
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 Figure. 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 matplotlib.pyplot as plt

torch.manual_seed(0)

# Create a small spectrogram as a 2D numpy array
# The function calls imshow on it, so it needs to be array-like with 2 dimensions
spectrogram = np.random.randn(4, 3)

ARGS = {
    'spectrogram': spectrogram
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Figure — a Figure output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Figure 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
scan_checkpoint Ran
ran; our contract draft was wrong, not the code
yxlu-0102/AP-BWE/inference/inference_16k.py
code served (permissive licence) · get_code("404632cb4f4669da")
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 str. 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 tempfile
import os

# Create a temporary directory for testing
temp_dir = tempfile.mkdtemp()

# Create some dummy checkpoint files to test the glob pattern
checkpoint_files = [
    os.path.join(temp_dir, "model_step_100.pt"),
    os.path.join(temp_dir, "model_step_200.pt"),
    os.path.join(temp_dir, "model_step_150.pt"),
]

# Create the dummy files
for cp_file in checkpoint_files:
    with open(cp_file, 'w') as f:
        f.write("dummy checkpoint")

ARGS = {
    "cp_dir": temp_dir,
    "prefix": "model_step_"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
stft Ran
ran; our contract draft was wrong, not the code
yxlu-0102/AP-BWE/cal_metrics.py
code served (permissive licence) · get_code("0637e0097af2a747")
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 4, 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

torch.manual_seed(0)

# Create a small audio tensor (batch_size=2, samples=4096)
audio = torch.randn(2, 4096)

ARGS = {
    "audio": audio,
    "n_fft": 2048,
    "hop_length": 512,
}
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 tuple, ndim 4, 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

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 14 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 3 the same month, 4 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
get_padding 53 other papers
37 dated earlier, 5 the same month, 8 later, 2 same year, order not determinable, 1 undated · 4 only as an assembly brick
1910.10838 (2019-10)
Zero-Shot Multi-Speaker Text-To-Speech with State-of-the-art Neural Speaker Embeddings
2006.04558 (2020-06)
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
2006.06873 (2020-06)
FastPitch: Parallel Text-to-speech with Pitch Prediction
and 50 more not named here
load_checkpoint 13 other papers
10 dated earlier, 1 the same month, 2 later
2010.05646 (2020-10)
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
2106.07889 (2021-06)
UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation
2203.02395 (2022-03)
iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform
and 10 more not named here
scan_checkpoint 10 other papers
7 dated earlier, 1 the same month, 2 later
2010.05646 (2020-10)
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
2203.02395 (2022-03)
iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform
2203.13086 (2022-03)
HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement
and 7 more not named here
get_padding_2d 3 other papers
2 dated earlier, 1 later
2308.08926 (2023-08)
Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancement
2405.06573 (2024-05)
An Investigation of Incorporating Mamba for Speech Enhancement
2608.12099 (2026-08)
RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation
get_dataset_filelist 1 other paper
1 dated earlier
2308.08926 (2023-08)
Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancement
plot_spectrogram 1 other paper
1 dated earlier
2308.08926 (2023-08)
Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancement

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

The majority of existing speech bandwidth extension (BWE) methods operate under the constraint of fixed source and target sampling rates, which limits their flexibility in practical applications. In this paper, we propose a multi-stage speech BWE model named MS-BWE, which can handle a set of source and target sampling rate pairs and achieve flexible extensions of frequency bandwidth. The proposed MS-BWE model comprises a cascade of BWE blocks, with each block featuring a dual-stream architecture to realize amplitude and phase extension, progressively painting the speech frequency bands stage by stage. The teacher-forcing strategy is employed to mitigate the discrepancy between training and inference. Experimental results demonstrate that our proposed MS-BWE is comparable to state-of-the-art speech BWE methods in speech quality. Regarding generation efficiency, the one-stage generation of MS-BWE can achieve over one thousand times real-time on GPU and about sixty times on CPU.

For agents

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

get_harvested_code_for_paper("2406.02250")
get_code_for_paper("2406.02250")
have("2406.02250")

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

curl https://syntology.ai/api/ran/2406.02250.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.02250.svg)](https://syntology.ai/paper/2406.02250)

Connect an agent — have() is free.