Papers › Keyword Transformer: A Self-Attention Model for Keyword Spotting

Keyword Transformer: A Self-Attention Model for Keyword Spotting

1 Apr 2021arXiv:2104.00769archive 2025-07-28

Axel Berg, Mark O'Connor, Miguel Tairum Cruz

The Transformer architecture has been successful across many domains, including natural language processing, computer vision and speech recognition. In keyword spotting, self-attention has primarily been used on top of convolutional or recurrent encoders. We investigate a range of ways to adapt the Transformer architecture to keyword spotting and introduce the Keyword Transformer (KWT), a fully self-attentional architecture that exceeds state-of-the-art performance across multiple tasks without any pre-training or additional data. Surprisingly, this simple architecture outperforms more complex models that mix convolutional, recurrent and attentive layers. KWT can be used as a drop-in replacement for these models, setting two new benchmark records on the Google Speech Commands dataset with 98.6% and 97.7% accuracy on the 12 and 35-command tasks respectively.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2104.00769")

Code

Syntology Ran 1 of 16 code samples harvested from 5 repositories linked to this paper; 15 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: community (archive-listed): 16 samples from 5 repositories, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ARM-software/keyword-transformer officialmentioned in papermentioned on GitHubtfApache-2.0 report
Arizona-Voice/Arizona-spotting mentioned on GitHubpytorchMIT report
ID56/Torch-KWT mentioned on GitHubpytorchMIT report
aau-es-ml/ssl_noise-robust_kws mentioned on GitHubpytorch report
holgerbovbjerg/data2vec-kws mentioned on GitHubpytorchMIT report
mashrurmorshed/torch-kwt mentioned on GitHubpytorch report
EscVM/EscVM_YT tfApache-2.0 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.

Code Syntology ran Syntology

16 samples harvested; 1 ran; 0 honoured the contract we drafted; 15 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
15unverified

Licence: 0 of the 16 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 5 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

find_consecutive_values phanxuanphucnd/Arizona-spotting/demo/app_kws.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 189d634a5204c3ef · report
calc_step ID56/Torch-KWT/utils/misc.py community (archive-listed) unverified MIT (permissive) · 12d715bdf737f38c · report
count_params ID56/Torch-KWT/utils/misc.py community (archive-listed) unverified MIT (permissive) · 854b6b5cf6315fbc · report
evaluate ID56/Torch-KWT/utils/trainer.py community (archive-listed) unverified MIT (permissive) · 40175e67a61190d6 · report
get_config ID56/Torch-KWT/config_parser.py community (archive-listed) unverified MIT (permissive) · d203ddadc113d9d6 · report
get_from_registry Arizona-Voice/Arizona-spotting/arizona_spotting/utils/misc_utils.py community (archive-listed) unverified MIT (permissive) · 90190d4490581c2d · report
get_label intelligentmachines/keyword_spotting_transformer/preprocessing.py community (archive-listed) unverified Apache-2.0 (permissive) · 4a28eb83a542016f · report
get_optimizer ID56/Torch-KWT/utils/opt.py community (archive-listed) unverified MIT (permissive) · d65ca06fe0124125 · report
get_preds mashrurmorshed/torch-kwt/inference.py community (archive-listed) unverified MIT (permissive) · 43893718a859b6fe · report
get_scheduler ID56/Torch-KWT/utils/scheduler.py community (archive-listed) unverified MIT (permissive) · d836a387836b9a38 · report
get_train_val_test_split ID56/Torch-KWT/utils/dataset.py community (archive-listed) unverified MIT (permissive) · 207ecf57a690304c · report
ifnone Arizona-Voice/Arizona-spotting/arizona_spotting/utils/misc_utils.py community (archive-listed) unverified MIT (permissive) · ea6f42601b6cb44e · report
kwt_from_name ID56/Torch-KWT/models/kwt.py community (archive-listed) unverified MIT (permissive) · d1bdc96cc20606ef · report
load_files intelligentmachines/keyword_spotting_transformer/preprocessing.py community (archive-listed) unverified Apache-2.0 (permissive) · cce294fcacc4be3b · report
str2bool Arizona-Voice/Arizona-spotting/arizona_spotting/utils/misc_utils.py community (archive-listed) unverified MIT (permissive) · 9e0b1e5fd4f77016 · report
train_single_batch ID56/Torch-KWT/utils/trainer.py community (archive-listed) unverified MIT (permissive) · 1aa66761878693ca · report

Tasks

Keyword SpottingSpeech Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Keyword Spotting Google Speech Commands KWT-3 Google Speech Commands V1 12 97.49 ±0.15 #5 of 42 Archive leaderboard report
Keyword Spotting Google Speech Commands KWT-3 Google Speech Commands V2 12 98.56 ±0.07 #5 of 42 Archive leaderboard report
Keyword Spotting Google Speech Commands KWT-3 Google Speech Commands V2 35 97.69 ±0.09 #5 of 42 Archive leaderboard report
Keyword Spotting Google Speech Commands KWT-2 Google Speech Commands V1 12 97.27 ±0.08 #8 of 42 Archive leaderboard report
Keyword Spotting Google Speech Commands KWT-2 Google Speech Commands V2 12 98.43±0.08 #8 of 42 Archive leaderboard report
Keyword Spotting Google Speech Commands KWT-2 Google Speech Commands V2 35 97.74 ±0.03 #8 of 42 Archive leaderboard report
Keyword Spotting Google Speech Commands KWT-1 Google Speech Commands V1 12 97.26±0.18 #9 of 42 Archive leaderboard report
Keyword Spotting Google Speech Commands KWT-1 Google Speech Commands V2 12 98.08±0.10 #9 of 42 Archive leaderboard report
Keyword Spotting Google Speech Commands KWT-1 Google Speech Commands V2 35 96.95±0.14 #9 of 42 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.

Methods

Absolute Position EncodingsAdamAttentionDense 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