SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.06185 · 2024

EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation

arXiv · PDF · Open in the Atlas

Code that ran

8 of 8 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 0 have no contract verdict; 7 failures of our instrument; 0 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/2406.06185.json · badge: /api/ran/2406.06185.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
sp-uhh/sgmse canonical (classifier label)
classifier basis: census
8 ran · 0 no recorded run
FunctionStatusWhere it lives
get_act Ran
ran; our contract draft was wrong, not the code
sp-uhh/sgmse/sgmse/backbones/ncsnpp_utils/layers.py
code served (permissive licence) · get_code("216c782f9d07ef3a")
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 ReLU. 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)

# The function takes a config parameter that is a string
# It checks the config against specific string values: 'elu', 'relu', 'lrelu', 'swish'
# and raises NotImplementedError for unrecognized values

ARGS = {
    'config': 'relu'
}
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 ReLU — a ReLU output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ReLU 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
get_activation Ran
ran; our contract draft was wrong, not the code
sp-uhh/sgmse/sgmse/backbones/dcunet.py
code served (permissive licence) · get_code("eb5ba43dadcbda84")
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 type. 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
from torch import nn

torch.manual_seed(0)

ARGS = {
    'name': 'silu'
}
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 type — a type output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a type 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
get_window Ran
ran, honoured the contract we drafted
sp-uhh/sgmse/sgmse/data_module.py
code served (permissive licence) · get_code("9e802d63089d5d62")
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 (512,) 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)

ARGS = {
    'window_type': 'hann',
    'window_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 Tensor, ndim 1, dtype family float, shape (512,) — shape (512,) 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
make_unet_encoder_decoder_args Ran
ran; our contract draft was wrong, not the code
sp-uhh/sgmse/sgmse/backbones/dcunet.py
code served (permissive licence) · get_code("9ce3b9f139bb58ff")
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

torch.manual_seed(0)

# Define encoder_args: list of (in_chan, out_chan, kernel_size, stride, padding, dilation)
# Each element is a tuple with the encoder configuration
encoder_args = [
    (3, 16, (3, 3), (1, 1), 'auto', (1, 1)),
    (16, 32, (3, 3), (2, 2), 'auto', (1, 1)),
    (32, 64, (3, 3), (2, 2), 'auto', (1, 1)),
]

# Define decoder_args: can be 'auto' or a list of (in_chan, out_chan, kernel_size, stride, padding, dilation, output_padding)
decoder_args = 'auto'

ARGS = {
    'encoder_args': encoder_args,
    'decoder_args': decoder_args,
}
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 — 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
ncsn_conv1x1 Ran
ran; our contract draft was wrong, not the code
sp-uhh/sgmse/sgmse/backbones/ncsnpp_utils/layers.py
pointer only (licence: MIT); the stored copy get_code serves, from SusanneSchaub/TPDM_Implant_Inpainting, is pointer only (licence: NONE) · get_code("85b2235eb7afaa4f")
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 SusanneSchaub/TPDM_Implant_Inpainting, 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.

torch_complex_from_reim Ran
ran; our contract draft was wrong, not the code
sp-uhh/sgmse/sgmse/backbones/shared.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
unet_decoder_args Ran
ran; our contract draft was wrong, not the code
sp-uhh/sgmse/sgmse/backbones/dcunet.py
code served (permissive licence) · get_code("0eabe078d2ed0794")
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 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 torch.nn as nn

# Construct encoder arguments
# Each encoder is a tuple of (in_chan, out_chan, kernel_size, stride, padding, dilation)
encoders = (
    (3, 16, 3, 2, 1, 1),      # First encoder: 3 input channels -> 16 output channels
    (16, 32, 3, 2, 1, 1),     # Second encoder: 16 input channels -> 32 output channels
    (32, 64, 3, 2, 1, 1),     # Third encoder: 32 input channels -> 64 output channels
)

ARGS = {
    "encoders": encoders,
    "skip_connections": 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 tuple, ndim 2, 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
variance_scaling Ran
ran; our contract draft was wrong, not the code
sp-uhh/sgmse/sgmse/backbones/ncsnpp_utils/layers.py
code served (permissive licence) · get_code("3ac11bfe0ae80195")
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 function. 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

torch.manual_seed(0)

ARGS = {
    'scale': 2.0,
    'mode': 'fan_in',
    'distribution': 'normal',
    'in_axis': 1,
    'out_axis': 0,
    'dtype': torch.float32,
    'device': 'cpu'
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 0 the same month, 2 later) and 0 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
variance_scaling 28 other papers
18 dated earlier, 10 later
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 25 more not named here
ncsn_conv1x1 19 other papers
11 dated earlier, 8 later
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 16 more not named here
torch_complex_from_reim 5 other papers
5 dated earlier
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
2008.00264 (2020-08)
DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement
and 2 more not named here
get_window 2 other papers
2 dated earlier
2212.11851 (2022-12)
StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation
2302.14748 (2023-02)
Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancement
get_act 1 other paper
1 dated earlier
2302.14748 (2023-02)
Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancement
get_activation 1 other paper
1 dated earlier
2302.14748 (2023-02)
Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancement
make_unet_encoder_decoder_args 1 other paper
1 dated earlier
2302.14748 (2023-02)
Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancement
unet_decoder_args 1 other paper
1 dated earlier
2302.14748 (2023-02)
Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based 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

We release the EARS (Expressive Anechoic Recordings of Speech) dataset, a high-quality speech dataset comprising 107 speakers from diverse backgrounds, totaling in 100 hours of clean, anechoic speech data. The dataset covers a large range of different speaking styles, including emotional speech, different reading styles, non-verbal sounds, and conversational freeform speech. We benchmark various methods for speech enhancement and dereverberation on the dataset and evaluate their performance through a set of instrumental metrics. In addition, we conduct a listening test with 20 participants for the speech enhancement task, where a generative method is preferred. We introduce a blind test set that allows for automatic online evaluation of uploaded data. Dataset download links and automatic evaluation server can be found online.

For agents

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

get_harvested_code_for_paper("2406.06185")
get_code_for_paper("2406.06185")
have("2406.06185")

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

curl https://syntology.ai/api/ran/2406.06185.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.06185.svg)](https://syntology.ai/paper/2406.06185)

Connect an agent — have() is free.