SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2212.09730 · 2022

Speaking Style Conversion in the Waveform Domain Using Discrete Self-Supervised Units

arXiv · PDF · Open in the Atlas

Code that ran

7 of 7 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 4 have no contract verdict; 2 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/2212.09730.json · badge: /api/ran/2212.09730.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
gallilmaimon/DISSC canonical (classifier label)
classifier basis not recorded on the link
7 ran · 0 no recorded run
FunctionStatusWhere it lives
discriminator_loss Ran
ran; our contract draft was wrong, not the code
gallilmaimon/DISSC/sr/models.py
pointer only (licence: MIT); the stored copy get_code serves, from zjzser/wmcodec, is pointer only (licence: NONE) · get_code("7137577cbef51217")
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 zjzser/wmcodec, 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.

feature_loss Ran
ran, honoured the contract we drafted
gallilmaimon/DISSC/sr/models.py
pointer only (licence: MIT); the stored copy get_code serves, from zjzser/wmcodec, is pointer only (licence: NONE) · get_code("e453b51f0ed5fb28")
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 zjzser/wmcodec, 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.

generator_loss Ran
ran; our contract draft was wrong, not the code
gallilmaimon/DISSC/sr/models.py
pointer only (licence: MIT); the stored copy get_code serves, from zjzser/wmcodec, is pointer only (licence: NONE) · get_code("1a9d74439d969cfd")
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 zjzser/wmcodec, 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.

init_loggers Ran
ran on a synthesized input
gallilmaimon/DISSC/utils.py
code served (permissive licence) · get_code("ce7d4703ab7af4e5")
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 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
import os

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

ARGS = {
    'path': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — 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
interp Ran
ran on a synthesized input
gallilmaimon/DISSC/utils.py
code served (permissive licence) · get_code("446926f352958627")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 1, dtype family float, shape (7,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
from scipy.interpolate import interp1d

def interp(vals, target_len):
    cur_len = len(vals)
    if cur_len == 1:
        return np.array(target_len * vals)
    if target_len == cur_len:
        return np.array(vals)
    return interp1d(np.linspace(0.0, 1.0, cur_len), vals, bounds_error=False, kind='nearest', fill_value=0)(np.linspace(0.0, 1.0, target_len))


# Create test arguments
vals = np.array([1.0, 2.0, 3.0, 4.0, 5.0])
target_len = 7

ARGS = {
    'vals': vals,
    'target_len': target_len
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (7,) — shape (7,) 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
len_carryover_correction Ran
ran on a synthesized input
gallilmaimon/DISSC/infer.py
code served (permissive licence) · get_code("d4f65f83536dd467")
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 int, shape (4,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function expects `lens` to be a tensor that:
# 1. Can be indexed with [0] to get a value/tensor
# 2. Has a .device attribute
# 3. Supports arithmetic operations (subtraction, addition)
# 4. Works with torch.round, torch.clamp, torch.tensor

# Based on the function body:
# - lens[0] is used with torch.clamp(lens[0], min=1)
# - The result is used in subtraction: (lens - ...)
# - The iteration happens over the first dimension: for n in a
# - lens.device is accessed

# Create a simple 2D tensor where:
# - First dimension has batch size 2
# - Second dimension has some values to iterate over
lens = torch.tensor([[2.5, 0.3, -0.8, 1.2], [1.0, 2.0, 3.0, 4.0]], dtype=torch.float32)

ARGS = {
    "lens": lens
}
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 int, shape (4,) — shape (4,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
morph_seq_len Ran
ran on a synthesized input
gallilmaimon/DISSC/utils.py
code served (permissive licence) · get_code("38a9379fee62c6f7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 1, dtype family float, shape (9,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
from itertools import groupby
from scipy.interpolate import interp1d

def interp(vals, target_len):
    cur_len = len(vals)
    if cur_len == 1:
        return np.array(target_len * vals)
    if target_len == cur_len:
        return np.array(vals)
    return interp1d(np.linspace(0.0, 1.0, cur_len), vals, bounds_error=False, kind='nearest', fill_value=0)(np.linspace(0.0, 1.0, target_len))

def morph_seq_len(units, pitch, t_lens):
    out = []
    for i, (k, g) in enumerate(groupby(zip(units, pitch), key=lambda x: x[0])):
        out.append(interp([f for _, f in g], t_lens[i]))
    return np.concatenate(out)

# Construct test arguments
# units: sequence of unit identifiers (e.g., phoneme indices)
# pitch: sequence of pitch values (floats) corresponding to each unit
# t_lens: list of target lengths for each group of units

units = [0, 0, 1, 1, 2]  # 5 elements: unit ids
pitch = [100.5, 101.2, 110.3, 112.1, 120.0]  # 5 elements: pitch values
t_lens = [3, 4, 2]  # 3 elements: target lengths for 3 groups

ARGS = {
    'units': units,
    'pitch': pitch,
    't_lens': t_lens
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (9,) — shape (9,) 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

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 3 the same month, 3 later) and 4 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
feature_loss 15 other papers
8 dated earlier, 1 the same month, 6 later
2006.04558 (2020-06)
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
2106.06103 (2021-06)
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
2106.07889 (2021-06)
UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation
and 12 more not named here
discriminator_loss 13 other papers
6 dated earlier, 1 the same month, 6 later
2006.04558 (2020-06)
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
2106.07889 (2021-06)
UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation
2109.13821 (2021-09)
Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme
and 10 more not named here
generator_loss 13 other papers
7 dated earlier, 1 the same month, 5 later
2006.04558 (2020-06)
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
2106.06103 (2021-06)
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
2106.07889 (2021-06)
UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation
and 10 more not named here

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 introduce DISSC, a novel, lightweight method that converts the rhythm, pitch contour and timbre of a recording to a target speaker in a textless manner. Unlike DISSC, most voice conversion (VC) methods focus primarily on timbre, and ignore people's unique speaking style (prosody). The proposed approach uses a pretrained, self-supervised model for encoding speech to discrete units, which makes it simple, effective, and fast to train. All conversion modules are only trained on reconstruction like tasks, thus suitable for any-to-many VC with no paired data. We introduce a suite of quantitative and qualitative evaluation metrics for this setup, and empirically demonstrate that DISSC significantly outperforms the evaluated baselines. Code and samples are available at https://pages.cs.huji.ac.il/adiyoss-lab/dissc/.

For agents

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

get_harvested_code_for_paper("2212.09730")
get_code_for_paper("2212.09730")
have("2212.09730")

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

curl https://syntology.ai/api/ran/2212.09730.json

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

[![Syntology run record](https://syntology.ai/api/ran/2212.09730.svg)](https://syntology.ai/paper/2212.09730)

Connect an agent — have() is free.