SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.03065 · 2022

Universal Speech Enhancement with Score-based Diffusion

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 0 have no contract verdict; 3 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/2206.03065.json · badge: /api/ran/2206.03065.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
line/open-universe reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
find_files Ran
ran; our contract draft was wrong, not the code
line/open-universe/open_universe/bin/enhance.py
code served (permissive licence) · get_code("65067ffb6e848832")
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 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.

from pathlib import Path
import tempfile
import os

# Create a temporary directory structure with audio files
temp_dir = tempfile.mkdtemp()
temp_path = Path(temp_dir)

# Create some audio files
(temp_path / "audio1.wav").touch()
(temp_path / "audio2.mp3").touch()
(temp_path / "audio3.flac").touch()
(temp_path / "other.txt").touch()

# Create a subdirectory with more audio files
subdir = temp_path / "subdir"
subdir.mkdir()
(subdir / "audio4.wav").touch()

ARGS = {
    "path": temp_path
}
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 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
prepare Ran
ran; our contract draft was wrong, not the code
line/open-universe/open_universe/bin/eval_metrics.py
code served (permissive licence) · get_code("4dbbc03ec894b2c1")
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 tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
from pathlib import Path
import json

# Create temporary directories for testing
temp_dir = tempfile.TemporaryDirectory()
temp_path = Path(temp_dir.name)

# Create ref_path directory with some reference .wav files
ref_path = temp_path / "ref"
ref_path.mkdir(exist_ok=True)
(ref_path / "audio1.wav").touch()
(ref_path / "audio2.wav").touch()

# Create deg_path directory with degraded .wav files
deg_path = temp_path / "deg"
deg_path.mkdir(exist_ok=True)
(deg_path / "audio1.wav").touch()
(deg_path / "audio2.wav").touch()
(deg_path / "audio3.wav").touch()

# Create results_path and pre-populate with some results
results_path = temp_path / "results.json"
initial_results = {
    "audio1": {"score": 0.95},
    "audio2": {"score": 0.87}
}
with open(results_path, 'w') as f:
    json.dump(initial_results, f)

ARGS = {
    "ref_path": ref_path,
    "deg_path": deg_path,
    "results_path": results_path
}
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 tuple, ndim 1, 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
summarize Ran
ran; our contract draft was wrong, not the code
line/open-universe/open_universe/bin/eval_metrics.py
code served (permissive licence) · get_code("fc7210125c834983")
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 dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
from collections import defaultdict

# Construct valid arguments for the summarize function
# The function expects:
# - results: a dict where values are dicts mapping metric names to numeric values (or strings)
# - ignore_inf: a boolean flag

results = {
    'experiment_1': {
        'accuracy': 0.95,
        'loss': 0.05,
        'f1_score': 0.92,
        'model_name': 'bert'  # string values should be skipped
    },
    'experiment_2': {
        'accuracy': 0.93,
        'loss': 0.07,
        'f1_score': 0.90,
        'description': 'baseline'  # string values should be skipped
    },
    'experiment_3': {
        'accuracy': 0.94,
        'loss': np.inf,  # infinite value to test ignore_inf parameter
        'f1_score': 0.91,
    }
}

ARGS = {
    'results': results,
    'ignore_inf': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 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
find_files 1 other paper
1 later
2406.12194 (2024-06)
Universal Score-based Speech Enhancement with High Content Preservation

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

Removing background noise from speech audio has been the subject of considerable effort, especially in recent years due to the rise of virtual communication and amateur recordings. Yet background noise is not the only unpleasant disturbance that can prevent intelligibility: reverb, clipping, codec artifacts, problematic equalization, limited bandwidth, or inconsistent loudness are equally disturbing and ubiquitous. In this work, we propose to consider the task of speech enhancement as a holistic endeavor, and present a universal speech enhancement system that tackles 55 different distortions at the same time. Our approach consists of a generative model that employs score-based diffusion, together with a multi-resolution conditioning network that performs enhancement with mixture density networks. We show that this approach significantly outperforms the state of the art in a subjective test performed by expert listeners. We also show that it achieves competitive objective scores with just 4-8 diffusion steps, despite not considering any particular strategy for fast sampling. We hope that both our methodology and technical contributions encourage researchers and practitioners to adopt a universal approach to speech enhancement, possibly framing it as a generative task.

For agents

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

get_harvested_code_for_paper("2206.03065")
get_code_for_paper("2206.03065")
have("2206.03065")

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

curl https://syntology.ai/api/ran/2206.03065.json

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

[![Syntology run record](https://syntology.ai/api/ran/2206.03065.svg)](https://syntology.ai/paper/2206.03065)

Connect an agent — have() is free.