Papers › TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech

TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech

12 Jul 2020arXiv:2007.06028archive 2025-07-28

Andy T. Liu, Shang-Wen Li, Hung-Yi Lee

We introduce a self-supervised speech pre-training method called TERA, which stands for Transformer Encoder Representations from Alteration. Recent approaches often learn by using a single auxiliary task like contrastive prediction, autoregressive prediction, or masked reconstruction. Unlike previous methods, we use alteration along three orthogonal axes to pre-train Transformer Encoders on a large amount of unlabeled speech. The model learns through the reconstruction of acoustic frames from their altered counterpart, where we use a stochastic policy to alter along various dimensions: time, frequency, and magnitude. TERA can be used for speech representations extraction or fine-tuning with downstream models. We evaluate TERA on several downstream tasks, including phoneme classification, keyword spotting, speaker recognition, and speech recognition. We present a large-scale comparison of various self-supervised models. TERA achieves strong performance in the comparison by improving upon surface features and outperforming previous models. In our experiments, we study the effect of applying different alteration techniques, pre-training on more data, and pre-training on various features. We analyze different model sizes and find that smaller models are strong representation learners than larger models, while larger models are more effective for downstream fine-tuning than smaller models. Furthermore, we show the proposed method is transferable to downstream datasets not used in pre-training.

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 repositories (andi611/Self-Supervised-Speech-Pretraining-and-Representation-Learning, s3prl/s3prl) is linked to this paper; the 14 samples below come from 2 community repositories. Syntology harvested code from andi611/Self-Supervised-Speech-Pretraining-and-Representation-Learning for another paper; from s3prl/s3prl for another paper.

andi611/Self-Supervised-Speech-Pretraining-and-Representation-Learning: Syntology's graph links these samples to Utilizing Self-supervised Representations for MOS Prediction (arXiv:2104.03017; that paper's own run record: 1 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; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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 14 code samples harvested from 2 repositories linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 14 samples from 2 repositories, 11 ran (7 with no instrument failure; 4 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 4 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 11 samples that ran has no recorded date.

andi611/Self-Supervised-Speech-Pretraining-and-Representation-Learning officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Utilizing Self-supervised Representations for MOS Prediction (arXiv:2104.03017; that paper's own run record: 1 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; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
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
592595/TERA mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional... (arXiv:1910.12638; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
Pandade1997/tera_asvproof mentioned on GitHubpytorchMITSyntology: 8 samples, 7 ran (4 instrument-failed) · 1 unverified report
Vernacular-ai/Multimodal-Slu mentioned on GitHubpytorchMITSyntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
idiap/apam mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
joselyn-rodriguez/s3prl mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SUPERB: Speech processing Universal PERformance Benchmark (arXiv:2105.01051; that paper's own run record: 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); 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

14 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 3 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.

1ran · honoured contract
3ran · our draft was wrong
1ran; the contract check could not run
6ran
3unverified

Licence: 3 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, 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 2 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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Pandade1997/tera_asvproof community (archive-listed) 8 samples, 7 ran (4 instrument-failed) · 1 unverified
swish in 258 papers
census: 14 implementations from 37 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
transformer/model.py ran · our draft was wrong fingerprinted MIT (permissive) · 0f786c407fb1ee4c · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
transformer/model.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · fdc64f4c72036ae4 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
gumbel_softmax in 82 papers
census: 19 implementations from 20 papers, 12 distinct outputs across 2 buckets, one shared input per bucket
transformer/model_quantize.py ran fingerprinted MIT (permissive) · 24b061a6d0af9f9e · report fixture: signature logits:Tensor/2/float, temperature:float/0/float · returned Tensor · level recorded 2026-09-24
gumbel_softmax_sample in 49 papers
census: 14 implementations from 16 papers, 4 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
transformer/model_quantize.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · 4650349b06b3d90f · report fixture: returned Tensor · level recorded 2026-09-22
load_model in 479 papers transformer/model_dual.py ran MIT (permissive) · 8b8e06d04c4faf7f · report fixture: signature transformer_model:callable/0/?, state_dict:dict/0/? · returned SimpleTransformer · level recorded 2026-09-24
prune_linear_layer in 40 papers transformer/model.py ran · our draft was wrong MIT (permissive) · d30d6c3098df2c42 · report fixture: signature layer:callable/0/?, index:Tensor/1/int, dim:int/0/int · returned Linear · level recorded 2026-09-22
sample_gumbel in 62 papers transformer/model_quantize.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · cec667e77fe8894d · report fixture: returned Tensor · level recorded 2026-09-22
test_transformer run_upstream.py unverified MIT (permissive) · 78826dfaa4289758 · report
Vernacular-ai/Multimodal-Slu community (archive-listed) 6 samples, 4 ran (0 instrument-failed) · 2 unverified
compare in 20 papers utility/get_best_score.py ran MIT (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
get_cosine_schedule_with_warmup in 42 papers schedulers.py ran MIT (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 schedulers.py ran MIT (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 optimizers.py ran MIT (permissive) · cecd81dc06f43149 · report fixture: signature model_params:list/1/callable · returned list · level recorded 2026-09-25
get_optimizer in 228 papers optimizers.py unverified MIT (permissive) · 15a4c381f6af50fb · report
get_scheduler in 122 papers schedulers.py unverified MIT (permissive) · 880bf296f53cdebf · report

Tasks

Keyword SpottingSelf-Supervised LearningSpeaker RecognitionSpeech RecognitionTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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