SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.00264 · 2020

DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement

arXiv · PDF · Open in the Atlas

Code that ran

14 of 15 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; 4 honoured the contract we drafted, 0 violated it and 8 have no contract verdict; 2 failures of our instrument; 1 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/2008.00264.json · badge: /api/ran/2008.00264.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
mpariente/asteroid canonical (classifier label)
classifier basis not recorded on the link
7 ran · 1 no recorded run
huyanxin/DeepComplexCRN canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
seorim0/DCCRN-with-various-loss-functions community (classifier label)
classifier basis: plan_row
4 ran · 0 no recorded run
FunctionStatusWhere it lives
batch_matrix_norm Ran
ran on a synthesized input
mpariente/asteroid/asteroid/losses/cluster.py
code served (permissive licence) · get_code("b191df325b6d1eb4")
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 1, dtype family float, shape (2,) 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 a small batch of matrices
# Shape: [batch=2, height=4, width=3]
matrix = torch.randn(2, 4, 3)

# norm_order parameter
norm_order = 2

ARGS = {
    "matrix": matrix,
    "norm_order": norm_order,
}
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 1, dtype family float, shape (2,) — shape (2,) 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
calculate_total_params Ran
ran, honoured the contract we drafted
seorim0/DCCRN-with-various-loss-functions/tester.py
code served (permissive licence) · get_code("43af741407c3119e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 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(SimpleModel, self).__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
        self.conv = nn.Conv2d(1, 2, kernel_size=3)
    
    def forward(self, x):
        return x

our_model = SimpleModel()

ARGS = {
    'our_model': our_model
}
Setup block drafted by
a language model, Claude Sonnet 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
check_silence_or_voice Ran
ran on a synthesized input
mpariente/asteroid/asteroid/binarize.py
code served (permissive licence) · get_code("2a6d8cfdd2b50c63")
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:
# - active: a List (used to store the result)
# - pair: a List containing tuples of (value, num_consecutive_occurrences)

# For the case where len(pair) == 1 (which makes check = True),
# the function will create a tensor based on the value
# Let's construct valid arguments

active = []  # Empty list to be populated by the function

# pair should be a list with one element: (value, num_consecutive_occurrences)
# value is a boolean-like, num_consecutive_occurrences is an int
pair = [(True, 5)]  # Single pair: value=True, num_consecutive_occurrences=5

ARGS = {
    "active": active,
    "pair": pair,
}
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
complex_cat Ran
ran on a synthesized input
seorim0/DCCRN-with-various-loss-functions/tools_for_model.py
code served (permissive licence) · get_code("82bb00176afbe510")
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

torch.manual_seed(0)

# The function takes inputs (a list of tensors) and axis (an int)
# Each tensor in inputs will be chunked into 2 parts along the specified axis
# So each tensor must have size >= 2 along that axis

# Create sample complex-valued tensors represented as [real_part, imag_part] concatenated
# Batch size 2, feature dim 4, so we need at least 2 along the axis we chunk
# Let's use axis=1 for chunking, so tensors should be (batch=2, features=8) 
# where the 8 represents [real_real_real_real, imag_imag_imag_imag]

tensor1 = torch.randn(2, 8)
tensor2 = torch.randn(2, 8)

inputs = [tensor1, tensor2]
axis = 1

ARGS = {
    "inputs": inputs,
    "axis": axis
}
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
count_same_pair Ran
ran on a synthesized input
mpariente/asteroid/asteroid/binarize.py
code served (permissive licence) · get_code("ca121622b4d58028")
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. 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
from itertools import groupby

torch.manual_seed(0)

# The function takes a list of lists containing binary sequences (0s and 1s)
# and returns a list of [value, consecutive_count] pairs for each sequence

ARGS = {
    "nums": [
        [0, 0, 1, 0],
        [1, 1, 1, 0, 0],
        [0, 1, 1, 0, 1, 1]
    ]
}
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 list — a list 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
deep_clustering_loss Ran
ran; our contract draft was wrong, not the code
mpariente/asteroid/asteroid/losses/cluster.py
code served (permissive licence) · get_code("af95819c66210a3f")
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 1, dtype family float, shape (2,) 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)

# Parameters for deep_clustering_loss
batch = 2
freq = 4
frames = 3
embedding_dim = 5
spk_cnt = 3

# embedding: shape (batch, freq*frames, embedding_dim)
embedding = torch.randn(batch, freq * frames, embedding_dim)

# tgt_index: shape (batch, freq, frames) with values in range [0, spk_cnt)
tgt_index = torch.randint(0, spk_cnt, (batch, freq, frames))

# binary_mask: shape (batch, freq*frames, 1)
binary_mask = torch.ones(batch, freq * frames, 1)

ARGS = {
    "embedding": embedding,
    "tgt_index": tgt_index,
    "binary_mask": binary_mask,
}
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 1, dtype family float, shape (2,) — shape (2,) 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
init_kernels Ran
ran on a synthesized input
seorim0/DCCRN-with-various-loss-functions/tools_for_model.py
code served (permissive licence) · get_code("f63be0bf29f7515a")
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
import numpy as np
from scipy.signal import get_window

torch.manual_seed(0)

ARGS = {
    'win_len': 16,
    'win_inc': 4,
    'fft_len': 32,
    'win_type': 'hann',
    'invers': False
}
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 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
is_torch_complex Ran
ran on a synthesized input
mpariente/asteroid/asteroid/complex_nn.py
code served (permissive licence) · get_code("0445a31bc868218d")
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 bool, 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)

# The function calls x.is_complex() on the argument x
# So x needs to be a torch tensor with the is_complex() method
# Create a complex tensor to test the function
complex_tensor = torch.complex(torch.randn(2, 4), torch.randn(2, 4))

ARGS = {
    "x": complex_tensor
}
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 bool, 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
l2_norm Ran
ran, honoured the contract we drafted
huyanxin/DeepComplexCRN/dc_crn.py
code served (permissive licence) · get_code("e150bca493a582c4")
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 Tensor, ndim 2, dtype family float, shape (2, 1) 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 two small tensors for s1 and s2
# The function performs element-wise multiplication and sums along the last dimension
# s1 and s2 should have compatible shapes for broadcasting
s1 = torch.randn(2, 4)  # batch_size=2, dim=4
s2 = torch.randn(2, 4)  # batch_size=2, dim=4

ARGS = {
    "s1": s1,
    "s2": s2,
}
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 Tensor, ndim 2, dtype family float, shape (2, 1) — shape (2, 1) 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
remove_dc Ran
ran, honoured the contract we drafted
huyanxin/DeepComplexCRN/dc_crn.py
code served (permissive licence) · get_code("535f1842272618e5")
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 Tensor, ndim 2, dtype family float, shape (2, 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 torch

torch.manual_seed(0)

# The function remove_dc takes a tensor 'data' and removes its mean along the last dimension
# It uses torch.mean with keepdim=True and basic tensor arithmetic
# We need to provide a tensor with at least 2 dimensions (since it operates on dimension -1)

data = torch.randn(2, 4)

ARGS = {
    "data": data
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
sdr Ran
ran on a synthesized input
seorim0/DCCRN-with-various-loss-functions/tools_for_loss.py
code served (permissive licence) · get_code("201c63500dea8042")
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 two small tensors for s1 and s2
# Shape: (batch_size=2, feature_dim=4)
s1 = torch.randn(2, 4)
s2 = torch.randn(2, 4)

ARGS = {
    "s1": s1,
    "s2": s2,
}
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
si_snr Ran
ran, honoured the contract we drafted
huyanxin/DeepComplexCRN/dc_crn.py
code served (permissive licence) · get_code("d2210dd1746c323d")
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 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 two small tensors for s1 and s2
# Shape: (batch_size=2, sequence_length=4)
# These represent audio signals or similar data
s1 = torch.randn(2, 4)
s2 = torch.randn(2, 4)

ARGS = {
    "s1": s1,
    "s2": s2,
    "eps": 1e-08,
}
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 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
torch_complex_from_magphase Ran
ran on a synthesized input
mpariente/asteroid/asteroid/complex_nn.py
code served (permissive licence) · get_code("d695a0f6cb2e24e3")
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, 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 torch

torch.manual_seed(0)

# Create small tensors for magnitude and phase
# mag: magnitude values (should be non-negative)
# phase: phase values in radians
mag = torch.rand(2, 4) * 2.0  # Small random magnitudes [0, 2)
phase = torch.rand(2, 4) * 2 * torch.pi  # Random phases [0, 2π)

ARGS = {
    "mag": mag,
    "phase": phase,
}
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, 4) — shape (2, 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
torch_complex_from_reim Ran
ran; our contract draft was wrong, not the code
mpariente/asteroid/asteroid/complex_nn.py
code served (permissive licence) · get_code("63cec12b7bc5275c")
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, 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create small real and imaginary tensors
re = torch.randn(2, 4)
im = torch.randn(2, 4)

ARGS = {
    "re": re,
    "im": im,
}
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, 4) — shape (2, 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
transform_to_binary_sequence Not yet run
unverified (harvested, no recorded run)
mpariente/asteroid/asteroid/binarize.py
code served (permissive licence) · get_code("3d60b6857fe0dc9d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 13 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 0 the same month, 10 later) and 2 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
torch_complex_from_reim 5 other papers
2 dated earlier, 3 later
1910.10400 (2019-10)
Filterbank design for end-to-end speech separation
2007.13975 (2020-07)
Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation
2010.04228 (2020-10)
All for One and One for All: Improving Music Separation by Bridging Networks
and 2 more not named here
batch_matrix_norm 3 other papers
2 dated earlier, 1 later
1910.10400 (2019-10)
Filterbank design for end-to-end speech separation
2007.13975 (2020-07)
Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation
2010.04228 (2020-10)
All for One and One for All: Improving Music Separation by Bridging Networks
deep_clustering_loss 3 other papers
2 dated earlier, 1 later
1910.10400 (2019-10)
Filterbank design for end-to-end speech separation
2007.13975 (2020-07)
Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation
2010.04228 (2020-10)
All for One and One for All: Improving Music Separation by Bridging Networks
is_torch_complex 3 other papers
2 dated earlier, 1 later
1910.10400 (2019-10)
Filterbank design for end-to-end speech separation
2007.13975 (2020-07)
Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation
2010.04228 (2020-10)
All for One and One for All: Improving Music Separation by Bridging Networks
torch_complex_from_magphase 3 other papers
2 dated earlier, 1 later
1910.10400 (2019-10)
Filterbank design for end-to-end speech separation
2007.13975 (2020-07)
Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation
2010.04228 (2020-10)
All for One and One for All: Improving Music Separation by Bridging Networks
check_silence_or_voice 2 other papers
1 dated earlier, 1 later
1910.10400 (2019-10)
Filterbank design for end-to-end speech separation
2010.04228 (2020-10)
All for One and One for All: Improving Music Separation by Bridging Networks
count_same_pair 2 other papers
1 dated earlier, 1 later
1910.10400 (2019-10)
Filterbank design for end-to-end speech separation
2010.04228 (2020-10)
All for One and One for All: Improving Music Separation by Bridging Networks
transform_to_binary_sequence 2 other papers
1 dated earlier, 1 later
1910.10400 (2019-10)
Filterbank design for end-to-end speech separation
2010.04228 (2020-10)
All for One and One for All: Improving Music Separation by Bridging Networks
calculate_total_params 1 other paper
1 later
2010.15508 (2020-10)
FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement
init_kernels 1 other paper
1 later
2204.03339 (2022-04)
Boosting Self-Supervised Embeddings for Speech Enhancement
l2_norm 1 other paper
1 dated earlier
1911.04697 (2019-11)
PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network
remove_dc 1 other paper
1 dated earlier
1911.04697 (2019-11)
PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network
si_snr 1 other paper
1 dated earlier
1911.04697 (2019-11)
PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network

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 enhancement has benefited from the success of deep learning in terms of intelligibility and perceptual quality. Conventional time-frequency (TF) domain methods focus on predicting TF-masks or speech spectrum, via a naive convolution neural network (CNN) or recurrent neural network (RNN). Some recent studies use complex-valued spectrogram as a training target but train in a real-valued network, predicting the magnitude and phase component or real and imaginary part, respectively. Particularly, convolution recurrent network (CRN) integrates a convolutional encoder-decoder (CED) structure and long short-term memory (LSTM), which has been proven to be helpful for complex targets. In order to train the complex target more effectively, in this paper, we design a new network structure simulating the complex-valued operation, called Deep Complex Convolution Recurrent Network (DCCRN), where both CNN and RNN structures can handle complex-valued operation. The proposed DCCRN models are very competitive over other previous networks, either on objective or subjective metric. With only 3.7M parameters, our DCCRN models submitted to the Interspeech 2020 Deep Noise Suppression (DNS) challenge ranked first for the real-time-track and second for the non-real-time track in terms of Mean Opinion Score (MOS).

For agents

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

get_harvested_code_for_paper("2008.00264")
get_code_for_paper("2008.00264")
have("2008.00264")

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

curl https://syntology.ai/api/ran/2008.00264.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.00264.svg)](https://syntology.ai/paper/2008.00264)

Connect an agent — have() is free.