Papers › SUPERB: Speech processing Universal PERformance Benchmark

SUPERB: Speech processing Universal PERformance Benchmark

3 May 2021arXiv:2105.01051archive 2025-07-28

Shu-wen Yang, Po-Han Chi, Yung-Sung Chuang, Cheng-I Jeff Lai, Kushal Lakhotia, Yist Y. Lin, Andy T. Liu, Jiatong Shi, Xuankai Chang, Guan-Ting Lin, Tzu-Hsien Huang, Wei-Cheng Tseng, Ko-tik Lee, Da-Rong Liu, Zili Huang, Shuyan Dong, Shang-Wen Li, Shinji Watanabe, Abdelrahman Mohamed, Hung-Yi Lee

Self-supervised learning (SSL) has proven vital for advancing research in natural language processing (NLP) and computer vision (CV). The paradigm pretrains a shared model on large volumes of unlabeled data and achieves state-of-the-art (SOTA) for various tasks with minimal adaptation. However, the speech processing community lacks a similar setup to systematically explore the paradigm. To bridge this gap, we introduce Speech processing Universal PERformance Benchmark (SUPERB). SUPERB is a leaderboard to benchmark the performance of a shared model across a wide range of speech processing tasks with minimal architecture changes and labeled data. Among multiple usages of the shared model, we especially focus on extracting the representation learned from SSL due to its preferable re-usability. We present a simple framework to solve SUPERB tasks by learning task-specialized lightweight prediction heads on top of the frozen shared model. Our results demonstrate that the framework is promising as SSL representations show competitive generalizability and accessibility across SUPERB tasks. We release SUPERB as a challenge with a leaderboard and a benchmark toolkit to fuel the research in representation learning and general speech processing.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (s3prl/s3prl) is linked to this paper; the 26 samples below come from 3 community repositories. Syntology harvested code from s3prl/s3prl for another paper.

s3prl/s3prl: Syntology's graph links these samples to Learning task-specific subspaces via interventional post-training of speech foundation models (arXiv:2606.17967; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method.

Syntology 26 code samples harvested from 3 repositories linked to this paper: 18 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 26 samples from 3 repositories, 18 ran (18 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

s3prl/s3prl officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning task-specific subspaces via interventional post-training of speech foundation models (arXiv:2606.17967; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
ashi-ta/speechglue mentioned on GitHubNOASSERTIONSyntology: not harvested report
joselyn-rodriguez/s3prl mentioned on GitHubpytorchApache-2.0Syntology: 11 samples, 8 ran (0 instrument-failed) · 3 unverified report
usc-sail/fed-ser-leakage mentioned on GitHubpytorchMITSyntology: 9 samples, 5 ran (0 instrument-failed) · 4 unverified report
usc-sail/fed-ser-semi mentioned on GitHubpytorchMITSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
vectominist/spin mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant... (arXiv:2305.11072; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

26 samples harvested: 18 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

18ran
8unverified

Licence: 1 of the 26 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

joselyn-rodriguez/s3prl community (archive-listed) 11 samples, 8 ran (0 instrument-failed) · 3 unverified
compare in 20 papers s3prl/utility/get_best_score.py ran Apache-2.0 (permissive) · 017e86bd00a963bc · report fixture: signature a:Tensor/0/float, b:Tensor/0/float, large_or_small:str/0/str · returned Tensor · level recorded 2026-09-25
default_collate_fn s3prl/dataio/collate_fn.py ran Apache-2.0 (permissive) · 329dce826f39f4ae · report fixture: signature samples:list/1/dict, padding_value:int/0/int · returned dict · level recorded 2026-09-24
get_cosine_schedule_with_warmup in 42 papers s3prl/schedulers.py ran Apache-2.0 (permissive) · 28936c41e64792bd · report fixture: signature optimizer:SGD/0/?, num_warmup_steps:int/0/int, num_training_steps:int/0/int, num_cycles:float/0/float, last_epoch:int/0/int · returned LambdaLR · level recorded 2026-09-25
get_cosine_with_hard_restarts_schedule_with_warmup in 5 papers s3prl/schedulers.py ran Apache-2.0 (permissive) · a9a4422e7a95a010 · report fixture: signature optimizer:SGD/0/?, num_warmup_steps:int/0/int, num_training_steps:int/0/int, num_cycles:int/0/int, last_epoch:int/0/int · returned LambdaLR · level recorded 2026-09-25
get_grouped_parameters s3prl/optimizers.py ran Apache-2.0 (permissive) · cecd81dc06f43149 · report fixture: signature model_params:list/1/callable · returned list · level recorded 2026-09-25
label_to_binary_vector s3prl/task/_hear_score.py ran Apache-2.0 (permissive) · 78bbfdb0f93b2535 · report fixture: signature label:list/1/int, num_labels:int/0/int · returned Tensor · level recorded 2026-09-24
label_vocab_as_dict s3prl/task/_hear_score.py ran Apache-2.0 (permissive) · b49c243b3b8f3268 · report fixture: signature df:DataFrame/0/?, key:str/0/str, value:str/0/str · returned dict · level recorded 2026-09-24
options in 6 papers s3prl/hub.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · e27f21a0984c5fa5 · report fixture: signature only_registered_ckpt:bool/0/bool · returned list · level recorded 2026-09-24
get_downstream_model s3prl/downstream/model.py unverified Apache-2.0 (permissive) · 1f49d1de2055d4d2 · report
get_optimizer in 228 papers s3prl/optimizers.py unverified Apache-2.0 (permissive) · 15a4c381f6af50fb · report
get_scheduler in 122 papers s3prl/schedulers.py unverified Apache-2.0 (permissive) · 880bf296f53cdebf · report
usc-sail/fed-ser-leakage community (archive-listed) 9 samples, 5 ran (0 instrument-failed) · 4 unverified
average_gradients in 20 papers mitigation/update.py ran MIT (permissive) · e5cb81a78546f033 · report fixture: signature g:list/1/list, num_samples_list:list/1/int · returned list · level recorded 2026-09-24
average_weights in 13 papers mitigation/update.py ran MIT (permissive) · 7dd1e77967fbe002 · report fixture: signature w:list/1/dict, num_samples_list:list/1/int · returned dict · level recorded 2026-09-24
privacy_account mitigation/federated_ser_classifier_udp.py ran MIT (permissive) · 97b2b0db606f1a48 · report fixture: signature args:Args/0/?, q_s:float/0/float, local_data_size:int/0/int, threshold_epochs:int/0/int · returned float64 · level recorded 2026-09-24
result_summary mitigation/update.py ran MIT (permissive) · 7bbf7ab0068988df · report fixture: signature step_outputs:list/1/dict · returned dict · level recorded 2026-09-24
save_result in 10 papers mitigation/federated_ser_classifier_udp.py ran MIT (permissive) · fbdf6d939f822660 · report fixture: signature save_index:int/0/int, acc:float/0/float, uar:float/0/float, best_epoch:int/0/int, dataset:str/0/str · returned DataFrame · level recorded 2026-09-24
read_data_dict_by_client mitigation/federated_ser_classifier_udp.py unverified MIT (permissive) · 45dc697ad626d1b9 · report
read_data_dict_by_client train/federated_ser_classifier.py unverified MIT (permissive) · 0b0ad265d320b59e · report
run_one_epoch train/federated_attribute_attack_result_finetune.py unverified MIT (permissive) · d8fff2eb3bd30b85 · report
run_one_epoch mitigation/federated_attribute_attack_result_per_speaker.py unverified MIT (permissive) · 72f8636db44a9139 · report
usc-sail/fed-ser-semi community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
get_class_weight utils/training_tools.py ran MIT (permissive) · aca9b1fc1e556086 · report fixture: signature labels_dict:dict/0/? · returned dict · level recorded 2026-09-24
pred_summary train/update_semi.py ran fingerprinted MIT (permissive) · 7770f3d31ebd7ead · report fixture: signature y_true:ndarray/1/int, y_pred:ndarray/1/int · returned dict · level recorded 2026-09-24
result_summary train/update_semi.py ran MIT (permissive) · 87228f82723818e0 · report fixture: signature step_outputs:list/1/dict · returned tuple · level recorded 2026-09-24
result_summary train/update.py ran MIT (permissive) · d250a779c880f432 · report fixture: signature step_outputs:list/1/dict · returned tuple · level recorded 2026-09-24
result_summary utils/training_tools.py ran MIT (permissive) · 3b6a45f6f66fde84 · report fixture: signature step_outputs:list/1/dict, mode:str/0/str, epoch:int/0/int · returned dict · level recorded 2026-09-24
read_data_dict_by_client train/federated_semi_ser_classifier.py unverified MIT (permissive) · 7db0a1f08a0e1867 · report

Tasks

Representation LearningSelf-Supervised Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections