SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.13018 · 2024

EMO-SUPERB: An In-depth Look at Speech Emotion Recognition

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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; 4 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/2402.13018.json · badge: /api/ran/2402.13018.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
EMOsuperb/EMO-SUPERB-submission canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
SCE_category Ran
ran; our contract draft was wrong, not the code
EMOsuperb/EMO-SUPERB-submission/emo-superb/expert.py
code served (permissive licence) · get_code("96594bd9f92d4736")
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
import torch.nn.functional as F

torch.manual_seed(0)

# Create small tensors for testing
batch_size = 2
num_classes = 4

# pred: logits tensor, shape (batch_size, num_classes)
pred = torch.randn(batch_size, num_classes)

# lab: one-hot encoded labels or class probabilities, shape (batch_size, num_classes)
lab = torch.zeros(batch_size, num_classes)
lab[0, 1] = 1.0  # First sample is class 1
lab[1, 2] = 1.0  # Second sample is class 2

# weights: not used in the function body, but required as parameter
weights = torch.ones(num_classes)

ARGS = {
    "pred": pred,
    "lab": lab,
    "weights": weights
}
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
class_balanced_softmax_cross_entropy_with_softtarget Ran
ran; our contract draft was wrong, not the code
EMOsuperb/EMO-SUPERB-submission/emo-superb/expert.py
code served (permissive licence) · get_code("e95dd45c97bd7ccc")
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)

# Parameters for the function
batch_size = 2
num_classes = 9

# input: (batch, num_classes) - logits before softmax
input_tensor = torch.randn(batch_size, num_classes)

# target: (batch, num_classes) - soft target distribution where each row sums to 1
target_tensor = torch.nn.functional.softmax(torch.randn(batch_size, num_classes), dim=1)

# weights: class weights from training set
weights_tensor = torch.tensor([0.2139, 0.3445, 0.4665, 3.3741, 0.3337, 2.2446, 0.2398, 1.3928, 0.3900])

# reduction mode
reduction_mode = 'mean'

ARGS = {
    'input': input_tensor,
    'target': target_tensor,
    'weights': weights_tensor,
    'reduction': reduction_mode
}
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
collate_fn_padd Ran
ran; our contract draft was wrong, not the code
EMOsuperb/EMO-SUPERB-submission/emo-superb/dataset.py
code served (permissive licence) · get_code("fefc9ff79bdd730c")
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 numpy as np
import torch

torch.manual_seed(0)

# Create sample batch items
# Each item is (wav, lab, utt, dur)
batch_item_1 = (
    np.array([0.1, 0.2, 0.3, 0.4, 0.5]),  # wav - variable length audio
    np.array([1, 0, 1, 0]),  # lab - labels
    "utterance_1",  # utt - utterance id
    5  # dur - duration
)

batch_item_2 = (
    np.array([0.15, 0.25, 0.35]),  # wav - different length
    np.array([0, 1, 1, 0]),  # lab - same shape labels
    "utterance_2",  # utt - utterance id
    3  # dur - duration
)

# Create batch list
batch = [batch_item_1, batch_item_2]

ARGS = {
    "batch": batch
}
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
get_norm_stat_for_wav Ran
ran, honoured the contract we drafted
EMOsuperb/EMO-SUPERB-submission/emo-superb/dataset.py
code served (permissive licence) · get_code("94da8efcd22778fc")
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 numpy as np
import torch

torch.manual_seed(0)

# Create a list of small numpy arrays simulating audio waveforms
wav_list = [
    np.array([0.1, 0.2, 0.3, 0.4], dtype=np.float32),
    np.array([0.15, 0.25, 0.35, 0.45], dtype=np.float32),
]

ARGS = {
    "wav_list": wav_list,
    "verbose": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, tqdm — 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
softmax_cross_entropy_with_softtarget Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
EMOsuperb/EMO-SUPERB-submission/emo-superb/expert.py
code served (permissive licence) · get_code("eb28d5d0f63ed885")
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
import torch.nn.functional as F

torch.manual_seed(0)

# Create input tensor: (batch_size=2, num_classes=4)
# This will be reshaped to (2, 4) in the function
input_tensor = torch.randn(2, 4, requires_grad=True)

# Create target tensor: (batch_size=2, num_classes=4)
# Each row must sum to 1 (valid probability distribution)
target_tensor = torch.tensor([
    [0.1, 0.2, 0.3, 0.4],
    [0.25, 0.25, 0.25, 0.25]
], dtype=torch.float32)

ARGS = {
    'input': input_tensor,
    'target': target_tensor,
    'reduction': 'mean'
}
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

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 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
softmax_cross_entropy_with_softtarget 3 other papers
2 dated earlier, 1 later · 1 only as an assembly brick
1911.05722 (2019-11)
Momentum Contrast for Unsupervised Visual Representation Learning
2209.15597 (2022-09)
MEIM: Multi-partition Embedding Interaction Beyond Block Term Format for Efficient and Expressive Link Prediction
2407.16574 (2024-07)
TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback

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 emotion recognition (SER) is a pivotal technology for human-computer interaction systems. However, 80.77% of SER papers yield results that cannot be reproduced. We develop EMO-SUPERB, short for EMOtion Speech Universal PERformance Benchmark, which aims to enhance open-source initiatives for SER. EMO-SUPERB includes a user-friendly codebase to leverage 15 state-of-the-art speech self-supervised learning models (SSLMs) for exhaustive evaluation across six open-source SER datasets. EMO-SUPERB streamlines result sharing via an online leaderboard, fostering collaboration within a community-driven benchmark and thereby enhancing the development of SER. On average, 2.58% of annotations are annotated using natural language. SER relies on classification models and is unable to process natural languages, leading to the discarding of these valuable annotations. We prompt ChatGPT to mimic annotators, comprehend natural language annotations, and subsequently re-label the data. By utilizing labels generated by ChatGPT, we consistently achieve an average relative gain of 3.08% across all settings.

For agents

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

get_harvested_code_for_paper("2402.13018")
get_code_for_paper("2402.13018")
have("2402.13018")

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

curl https://syntology.ai/api/ran/2402.13018.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.13018.svg)](https://syntology.ai/paper/2402.13018)

Connect an agent — have() is free.