Keyword Transformer: A Self-Attention Model for Keyword Spotting
Open accessThe DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Abstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · arXiv · doi:10.48550/arxiv.2005.12872 · Cited by 18,253
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
Davis, S., & Mermelstein, P. (1980) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/tassp.1980.1163420 · Cited by 5,465
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Park, D. S., Chan, W., Zhang, Y., Chiu, C.-C., Zoph, B., Cubuk, E. D., & Le, Q. V. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-2680 · Cited by 3,558
Conformer: Convolution-augmented Transformer for Speech Recognition
Gulati, A., Qin, J., Chiu, C.-C., Parmar, N., Zhang, Y., Yu, J., Han, W., Wang, S., Zhang, Z., Wu, Y., et al. (2020) · Interspeech 2020 · doi:10.21437/interspeech.2020-3015 · Cited by 3,150
Conformer: Convolution-augmented Transformer for Speech Recognition
Gulati, A., Qin, J., Chiu, C.-C., Parmar, N., Zhang, Y., Yu, J., Han, W., Wang, S., Zhang, Z., Wu, Y., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.08100 · Cited by 3,150
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Z., Tay, F. E., Feng, J., & Yan, S. (2021) · arXiv · doi:10.48550/arxiv.2101.11986 · Cited by 2,415
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Z., Tay, F. E. H., Feng, J., & Yan, S. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00060 · Cited by 2,415 · cited 1×
“image classification, [2, 3, 4], image colorization [5], object detection [6], automatic speech recognition [7, 8, 9], video classification [10] and multi-agent spatiotemporal modeling [11].”
BackgroundSelf-Training With Noisy Student Improves ImageNet Classification
Xie, Q., Luong, M.-T., Hovy, E., & Le, Q. V. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01070 · Cited by 2,393
Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
Warden, P. (2018) · arXiv · doi:10.48550/arxiv.1804.03209 · Cited by 1,033 · cited 3×
“Inspired by the strength of the simple Vision Transformer (ViT) model [2] in computer vision and by the techniques that improves its data-efficiency [3], we propose an adaptation of this architecture for keyword spotting and find that it matches or outperforms existing models on the much smaller Google Speech Commands…”
MethodMobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices
Sun, Z., Yu, H., Song, X., Liu, R., Yang, Y., & Zhou, D. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.195 · Cited by 757
Neimark, D., Bar, O., Zohar, M., & Asselmann, D. (2021) · 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw54120.2021.00355 · Cited by 551 · cited 1×
“image classification, [2, 3, 4], image colorization [5], object detection [6], automatic speech recognition [7, 8, 9], video classification [10] and multi-agent spatiotemporal modeling [11].”
BackgroundSpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning
Wang, H., Zhang, Z., & Han, S. (2021) · 2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca51647.2021.00018 · Cited by 427 · cited 1×
“5x latency reduction through model compression [34] and up to 4059x energy reduction through sparsity and hardware codesign [35].”
Background
Cited by
A review of deep learning techniques for speech processing
Mehrish, A., Majumder, N., Bharadwaj, R., Mihalcea, R., & Poria, S. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101869 · Cited by 389
Ssast: Self-supervised audio spectrogram transformer
Gong, Y., Lai, C.-I., Chung, Y.-A., & Glass, J. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i10.21315 · Cited by 294
HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection
Chen, K., Du, X., Zhu, B., Ma, Z., Berg-Kirkpatrick, T., & Dubnov, S. (2022) · ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp43922.2022.9746312 · Cited by 294
Action Transformer: A self-attention model for short-time pose-based human action recognition
Mazzia, V., Angarano, S., Salvetti, F., Angelini, F., & Chiaberge, M. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2021.108487 · Cited by 276
Unified Keyword Spotting and Audio Tagging on Mobile Devices with Transformers
Dinkel, H., Wang, Y., Yan, Z., Zhang, J., & Wang, Y. (2023) · ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp49357.2023.10095534 · Cited by 4
“…while Approach #Params (M) GSCV1 AS TC-ResNet8 [5] 0.06 96.10 - NAS2 [6] 0.88 97.22 - MEGA [28] 0.3 96.92 - MatchBoxNet [29] 0.5 96.83 - KWT-1 [10] 0.6 97.05 - LETR-128 [11] 0.6 97.61 - LETR-256 [11] 1.1 97.85 - KWT-2 [10] 2.4 97.36 - KWT-3 [10] 5.3 97.24 - Wav2KWS [30] 225 97.90 - MBv2 [31]…”
BackgroundInfluential
Metadata
- Authors
- Berg, A., O’Connor, M., & Cruz, M. T.
- Venue
- Interspeech 2021
- Publisher
- ISCA
- Published
- 2021-08-30
- Pages
- 4249-4253
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W3141838378
- Cited by
- 147
- References
- 16
- FWCI
- 13.08
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.