Papers › SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition

SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition

18 Apr 2019arXiv:1904.08779archive 2025-07-28

Daniel S. Park, William Chan, Yu Zhang, Chung-Cheng Chiu, Barret Zoph, Ekin D. Cubuk, Quoc V. Le

We present SpecAugment, a simple data augmentation method for speech recognition. SpecAugment is applied directly to the feature inputs of a neural network (i.e., filter bank coefficients). The augmentation policy consists of warping the features, masking blocks of frequency channels, and masking blocks of time steps. We apply SpecAugment on Listen, Attend and Spell networks for end-to-end speech recognition tasks. We achieve state-of-the-art performance on the LibriSpeech 960h and Swichboard 300h tasks, outperforming all prior work. On LibriSpeech, we achieve 6.8% WER on test-other without the use of a language model, and 5.8% WER with shallow fusion with a language model. This compares to the previous state-of-the-art hybrid system of 7.5% WER. For Switchboard, we achieve 7.2%/14.6% on the Switchboard/CallHome portion of the Hub5'00 test set without the use of a language model, and 6.8%/14.1% with shallow fusion, which compares to the previous state-of-the-art hybrid system at 8.3%/17.3% WER.

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

Syntology 18 code samples harvested from 6 repositories linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 18 samples from 6 repositories, 14 ran (13 with no instrument failure; 1 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 10 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

30 repositories listed; official and paper-mentioned ones first.

AmirmohammadRostami/KeywordsSpotting-EfficientNet-A0 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946; that paper's own run record: 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified); nothing checks that they implement this paper's method. report
Audio-WestlakeU/RCT-Random-Consistency-Training mentioned on GitHubpytorchSyntology: not harvested report
DemisEom/SpecAugment mentioned on GitHubpytorchApache-2.0Syntology: 7 samples, 4 ran (0 instrument-failed) · 3 unverified report
HLasse/wav2vec_finetune mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unsupervised Cross-lingual Representation Learning for Speech Recognition (arXiv:2006.13979; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
HeleneFabia/keyword-spotter mentioned on GitHubpytorchSyntology: not harvested report
KimJeongSun/SpecAugment_numpy_scipy mentioned on GitHubtfApache-2.0Syntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
MichaelisTrofficus/spec_augment mentioned on GitHubtfMITSyntology: not harvested report
SarthakYadav/audax mentioned on GitHubjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to mixup: Beyond Empirical Risk Minimization (arXiv:1710.09412; that paper's own run record: 36 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 22 where Syntology's instrument failed) · 11 unverified), LEAF: A Learnable Frontend for Audio Classification (arXiv:2101.08596; that paper's own run record: 14 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 12 unverified) and A ConvNet for the 2020s (arXiv:2201.03545; that paper's own run record: 57 ran (of which 39 constructed an object rather than computing a result; 49 with no instrument failure: 2 honoured, 0 violated, 47 with no contract checked; 8 where Syntology's instrument failed) · 23 unverified); nothing checks that they implement this paper's method. report
ZhengkunTian/OpenTransformer mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
ahmedalbahnasawy/spec_torch_kaldi-compatibility mentioned on GitHubSyntology: not harvested report
andychinka/dcase-challenge mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to mixup: Beyond Empirical Risk Minimization (arXiv:1710.09412; that paper's own run record: 36 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 22 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
audio-westlakeu/rct mentioned on GitHubpytorchSyntology: not harvested report
biyoml/End-to-End-Mandarin-ASR mentioned on GitHubpytorchSyntology: not harvested report
cosmoquester/speech-recognition mentioned on GitHubtfMITSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
ebouteillon/freesound-audio-tagging-2019 mentioned on GitHubpytorchMITSyntology: not harvested report
freds0/data_augmentation_for_asr mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
google-research/leaf-audio mentioned on GitHubtfSyntology: not harvested report
hgstudent/las mentioned on GitHubtfSyntology: not harvested report
iver56/audiomentations mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AudioCLIP: Extending CLIP to Image, Text and Audio (arXiv:2106.13043; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
jackjhliu/End-to-End-Mandarin-ASR mentioned on GitHubpytorchSyntology: not harvested report
kimjeongsun/specaugment mentioned on GitHubpytorchApache-2.0Syntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
lRomul/argus-freesound mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to mixup: Beyond Empirical Risk Minimization (arXiv:1710.09412; that paper's own run record: 36 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 22 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
mozilla/DeepSpeech mentioned on GitHubtfMPL-2.0Syntology: not harvested report
park-cheol/ASR-Conformer mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context (arXiv:1901.02860; that paper's own run record: 67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified); nothing checks that they implement this paper's method. report
shelling203/SpecAugment mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
shuaijiang/Whisper-Finetune mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
viig99/mixmatch-freesound mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MixMatch: A Holistic Approach to Semi-Supervised Learning (arXiv:1905.02249; that paper's own run record: 47 ran (of which 8 constructed an object rather than computing a result; 27 with no instrument failure: 8 honoured, 0 violated, 19 with no contract checked; 20 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
PaddlePaddle/PaddleSpeech paddleApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A³T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing (arXiv:2203.09690; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
makcedward/nlpaug tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost (arXiv:2203.07860; that paper's own run record: 6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
sh951011/Korean-Speech-Recognition pytorchApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified 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

18 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 4 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 · our draft was wrong
13ran
4unverified

Licence: 0 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 6 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.

DemisEom/SpecAugment community (archive-listed) 7 samples, 4 ran (0 instrument-failed) · 3 unverified
freq_mask SpecAugment/sparse_image_warp_pytorch.py ran Apache-2.0 (permissive) · 5c640f85e661f5c9 · report fixture: signature spec:Tensor/3/float, F:int/0/int, num_masks:int/0/int, replace_with_zero:bool/0/bool · returned Tensor · level recorded 2026-09-24
frequency_masking SpecAugment/spec_augment_tensorflow.py ran Apache-2.0 (permissive) · b8b1c17d15f3c463 · report fixture: signature mel_spectrogram:EagerTensor/4/float, v:EagerTensor/0/int, frequency_masking_para:int/0/int, frequency_mask_num:int/0/int · returned EagerTensor · level recorded 2026-09-24
time_mask in 5 papers SpecAugment/sparse_image_warp_pytorch.py ran Apache-2.0 (permissive) · 649daef969b655ed · report fixture: signature spec:Tensor/3/float, T:int/0/int, num_masks:int/0/int, replace_with_zero:bool/0/bool · returned Tensor · level recorded 2026-09-24
time_warp in 5 papers SpecAugment/sparse_image_warp_pytorch.py ran Apache-2.0 (permissive) · d94ba36bc01eda60 · report fixture: returned Tensor · level recorded 2026-09-24
dense_image_warp SpecAugment/sparse_image_warp_np.py unverified Apache-2.0 (permissive) · a67846a111580cfb · report
sparse_image_warp_np SpecAugment/sparse_image_warp_np.py unverified Apache-2.0 (permissive) · ff652f83fe897b32 · report
time_masking SpecAugment/spec_augment_tensorflow.py unverified Apache-2.0 (permissive) · fdad4c356de2036b · report
KimJeongSun/SpecAugment_numpy_scipy community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
liftPts specaugment.py ran Apache-2.0 (permissive) · be893d0ee5559ea0 · report fixture: signature p:ndarray/2/float, cp:ndarray/2/float · returned ndarray · level recorded 2026-09-24
makeT specaugment.py ran Apache-2.0 (permissive) · 7fd389e1e9203afa · report fixture: signature cp:ndarray/2/float · returned ndarray · level recorded 2026-09-24
ZhengkunTian/OpenTransformer community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
spec_augment otrans/data/augment.py ran · our draft was wrong MIT (permissive) · aabacfe520817be6 · report fixture: signature mel_spectrogram:ndarray/2/float, freq_mask_num:int/0/int, time_mask_num:int/0/int, freq_mask_rate:float/0/float, time_mask_rate:float/0/float, max_mask_time_len:int/0/int · returned ndarray · level recorded 2026-09-22
cosmoquester/speech-recognition community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
get_device_strategy speech_recognition/utils.py ran MIT (permissive) · 3046ea943ba309f2 · report fixture: signature device:str/0/str · returned OneDeviceStrategy · level recorded 2026-09-24
get_logger in 383 papers speech_recognition/utils.py ran MIT (permissive) · 0c8faeedf5a5c01a · report fixture: signature name:str/0/str · returned Logger · level recorded 2026-09-24
get_rnn_cls speech_recognition/models/las.py ran MIT (permissive) · aa9757e8039b3c4a · report fixture: signature rnn_type:str/0/str · returned type · level recorded 2026-09-24
get_tfrecord_dataset speech_recognition/data.py ran MIT (permissive) · ba904be9deeb14d4 · report fixture: signature dataset_paths:str/0/str · returned _MapDataset · level recorded 2026-09-24
levenshtein_distance in 18 papers speech_recognition/utils.py ran MIT (permissive) · 2046b512475f2561 · report fixture: signature truth:str/0/str, hypothesis:str/0/str, normalize:bool/0/bool · returned float64 · level recorded 2026-09-24
kimjeongsun/specaugment community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
spec_augment SpecAugment/spec_augment_pytorch.py ran Apache-2.0 (permissive) · ed8e1a9c22ce7ac6 · report fixture: signature mel_spectrogram:ndarray/2/float, time_warping_para:int/0/int, frequency_masking_para:int/0/int, time_masking_para:int/0/int, frequency_mask_num:int/0/int, time_mask_num:int/0/int · returned ndarray · level recorded 2026-09-24
sparse_image_warp SpecAugment/sparse_image_warp_pytorch.py unverified Apache-2.0 (permissive) · aa191294fe80e2d4 · report
sh951011/Korean-Speech-Recognition community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
check_envirionment kospeech/utils.py ran Apache-2.0 (permissive) · 8365bd2bebaeee71 · report fixture: signature use_cuda:bool/0/bool · returned device · level recorded 2026-09-24

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data AugmentationLanguage ModelingLanguage ModellingSpeech Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Recognition Hub5'00 SwitchBoard LAS + SpecAugment (with LM, Switchboard mild policy) CallHome 14.6 #1 of 5 Archive leaderboard report
Speech Recognition Hub5'00 SwitchBoard LAS + SpecAugment (with LM, Switchboard mild policy) SwitchBoard 6.8 #1 of 5 Archive leaderboard report
Speech Recognition Hub5'00 SwitchBoard LAS + SpecAugment (with LM, Switchboard strong policy) CallHome 14 #2 of 5 Archive leaderboard report
Speech Recognition Hub5'00 SwitchBoard LAS + SpecAugment (with LM, Switchboard strong policy) SwitchBoard 7.1 #2 of 5 Archive leaderboard report
Speech Recognition LibriSpeech test-clean LAS + SpecAugment Word Error Rate (WER) 2.5 #39 of 64 Archive leaderboard report
Speech Recognition LibriSpeech test-clean LAS (no LM) Word Error Rate (WER) 2.7 #42 of 64 Archive leaderboard report
Speech Recognition LibriSpeech test-other LAS + SpecAugment Word Error Rate (WER) 5.8 #36 of 53 Archive leaderboard report
Speech Recognition LibriSpeech test-other LAS (no LM) Word Error Rate (WER) 6.5 #39 of 53 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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