SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.07889 · 2021

UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation

arXiv · PDF · Open in the Atlas

Code that ran

11 of 12 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, 2 violated it and 0 have no contract verdict; 7 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/2106.07889.json · badge: /api/ran/2106.07889.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
rishikksh20/UnivNet-pytorch community (classifier label)
classifier basis not recorded on the link
9 ran · 1 no recorded run
neonbjb/tortoise-tts reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
discriminator_loss Ran
ran; our contract draft was wrong, not the code
rishikksh20/UnivNet-pytorch/loss.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.

dynamic_range_compression Ran
ran, violated the contract we drafted
rishikksh20/UnivNet-pytorch/meldataset.py
code served (permissive licence) · get_code("be031b15a988a556")
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 (8,) 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

# Construct a small numpy array as input
x = np.array([0.00001, 0.0001, 0.001, 0.01, 0.1, 1.0, 10.0, 100.0])

# Define arguments dict with all parameters
ARGS = {
    "x": x,
    "C": 1,
    "clip_val": 1e-05
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — 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 (8,) — shape (8,) 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
dynamic_range_decompression Ran
ran, violated the contract we drafted
rishikksh20/UnivNet-pytorch/meldataset.py
code served (permissive licence) · get_code("9e30e7d510c9d341")
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 (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 numpy as np

# The function takes two parameters: x and C
# x is expected to be a numpy array (based on np.exp(x) operation)
# C is a scalar value used for division (default is 1)

# Create a small numpy array for x
x = np.array([0.5, 1.0, 1.5, 2.0])

# Create a scalar value for C
C = 2.0

ARGS = {
    "x": x,
    "C": C
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — 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 (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
feature_loss Ran
ran, honoured the contract we drafted
rishikksh20/UnivNet-pytorch/loss.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
rishikksh20/UnivNet-pytorch/loss.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.

get_padding Ran
ran, honoured the contract we drafted
rishikksh20/UnivNet-pytorch/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.

load_checkpoint Ran
ran; our contract draft was wrong, not the code
rishikksh20/UnivNet-pytorch/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from zjzser/traceablespeech, is pointer only (licence: NONE) · get_code("19c9fe23dc000c61")
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/traceablespeech, 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.

load_wav Ran
ran; our contract draft was wrong, not the code
rishikksh20/UnivNet-pytorch/meldataset.py
pointer only (licence: MIT); the stored copy get_code serves, from nku-hlt/audioeditor, is pointer only (licence: NOASSERTION) · get_code("8043eaefe4c09c1f")
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 nku-hlt/audioeditor, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

pad_or_truncate Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
neonbjb/tortoise-tts/tortoise/api.py
code served (permissive licence) · get_code("ef08b07bfdc86c88")
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 Tensor, ndim 2, dtype family float, shape (2, 8) 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 tensor to test pad_or_truncate
# Using a 2D tensor with shape (2, 5) where 5 is the sequence length dimension
t = torch.randn(2, 5)

# Target length to pad or truncate to
length = 8

ARGS = {
    "t": t,
    "length": length
}
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 Tensor, ndim 2, dtype family float, shape (2, 8) — shape (2, 8) 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
plot_spectrogram Ran
ran; our contract draft was wrong, not the code
rishikksh20/UnivNet-pytorch/utils.py
code served (permissive licence) · get_code("8520e6e61b8bf789")
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-like 2D array
# Spectrograms are typically (frequency_bins, time_steps)
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
read_lexicon Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from KevinMIN95/StyleSpeech
pointer only · get_code("2b5c06c1ba593c3c")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

stft Not yet run
unverified (harvested, no recorded run)
rishikksh20/UnivNet-pytorch/stft_loss.py
code served (permissive licence) · get_code("d40b7ea72ed329ed")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 12 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 4 the same month, 11 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
get_padding 53 other papers
5 dated earlier, 2 the same month, 45 later, 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
feature_loss 15 other papers
1 dated earlier, 1 the same month, 13 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
2109.13821 (2021-09)
Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme
and 12 more not named here
discriminator_loss 13 other papers
1 dated earlier, 12 later
2006.04558 (2020-06)
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
2109.13821 (2021-09)
Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme
2203.02395 (2022-03)
iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform
and 10 more not named here
dynamic_range_compression 13 other papers
1 dated earlier, 12 later
2006.04558 (2020-06)
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
2110.12676 (2021-10)
Controllable and Interpretable Singing Voice Decomposition via Assem-VC
2202.13277 (2022-02)
Learning the Beauty in Songs: Neural Singing Voice Beautifier
and 10 more not named here
dynamic_range_decompression 13 other papers
1 dated earlier, 12 later
2006.04558 (2020-06)
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
2110.12676 (2021-10)
Controllable and Interpretable Singing Voice Decomposition via Assem-VC
2202.13277 (2022-02)
Learning the Beauty in Songs: Neural Singing Voice Beautifier
and 10 more not named here
generator_loss 13 other papers
1 dated earlier, 1 the same month, 11 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
2109.13821 (2021-09)
Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme
and 10 more not named here
load_checkpoint 13 other papers
1 dated earlier, 12 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 10 more not named here
read_lexicon 11 other papers
6 dated earlier, 2 the same month, 3 later
1905.09263 (2019-05)
FastSpeech: Fast, Robust and Controllable Text to Speech
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 8 more not named here
load_wav 9 other papers
1 dated earlier, 8 later
2006.04558 (2020-06)
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
2110.12676 (2021-10)
Controllable and Interpretable Singing Voice Decomposition via Assem-VC
2202.13277 (2022-02)
Learning the Beauty in Songs: Neural Singing Voice Beautifier
and 6 more not named here
plot_spectrogram 7 other papers
1 dated earlier, 6 later
2006.04558 (2020-06)
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
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 4 more not named here
stft 3 other papers
3 dated earlier
1910.11480 (2019-10)
Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram
2005.05106 (2020-05)
Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speech
2010.15508 (2020-10)
FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement
pad_or_truncate 1 other paper
1 later
2305.07243 (2023-05)
Better speech synthesis through scaling

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

Most neural vocoders employ band-limited mel-spectrograms to generate waveforms. If full-band spectral features are used as the input, the vocoder can be provided with as much acoustic information as possible. However, in some models employing full-band mel-spectrograms, an over-smoothing problem occurs as part of which non-sharp spectrograms are generated. To address this problem, we propose UnivNet, a neural vocoder that synthesizes high-fidelity waveforms in real time. Inspired by works in the field of voice activity detection, we added a multi-resolution spectrogram discriminator that employs multiple linear spectrogram magnitudes computed using various parameter sets. Using full-band mel-spectrograms as input, we expect to generate high-resolution signals by adding a discriminator that employs spectrograms of multiple resolutions as the input. In an evaluation on a dataset containing information on hundreds of speakers, UnivNet obtained the best objective and subjective results among competing models for both seen and unseen speakers. These results, including the best subjective score for text-to-speech, demonstrate the potential for fast adaptation to new speakers without a need for training from scratch.

For agents

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

get_harvested_code_for_paper("2106.07889")
get_code_for_paper("2106.07889")
have("2106.07889")

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

curl https://syntology.ai/api/ran/2106.07889.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.07889.svg)](https://syntology.ai/paper/2106.07889)

Connect an agent — have() is free.