mlsanityData to 7 Oct 2026

A neural attention model for speech command recognition

arXiv 1808.08929 ↗First posted 27 Aug 2018eess.AS cs.SDcited by 44

Not on the map. Why?

Abstract (arXiv)

This paper introduces a convolutional recurrent network with attention for speech command recognition. Attention models are powerful tools to improve performance on natural language, image captioning and speech tasks. The proposed model establishes a new state-of-the-art accuracy of 94.1% on Google Speech Commands dataset V1 and 94.5% on V2 (for the 20-commands recognition task), while still keeping a small footprint of only 202K trainable parameters. Results are compared with previous convolutional implementations on 5 different tasks (20 commands recognition (V1 and V2), 12 commands recognition (V1), 35 word recognition (V1) and left-right (V1)). We show detailed performance results and demonstrate that the proposed attention mechanism not only improves performance but also allows inspecting what regions of the audio were taken into consideration by the network when outputting a given category.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 8; 2023: 6; 2024: 7; 2025: 3; 2026: 3.

44 papers.

Sort:

By area:

  1. 2021Accurate and efficient time-domain classification with adaptive spiking recurrent neural networkscited by 113
  2. 2021Voice2Series: Reprogramming Acoustic Models for Time Series Classificationcited by 91
  3. 2021Keyword Transformer: A Self-Attention Model for Keyword Spottingcited by 59
  4. 2023A Survey on Time-Series Pre-Trained Modelscited by 52
  5. 2021Broadcasted Residual Learning for Efficient Keyword Spottingcited by 47
  6. 2021Deep Spoken Keyword Spotting: An Overviewcited by 43
  7. 2021Can You Hear It? Backdoor Attacks via Ultrasonic Triggerscited by 41
  8. 2023Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Soundcited by 28
  9. 2021Learning Efficient Representations for Keyword Spotting with Triplet Losscited by 24
  10. 2021Backpropagation with Biologically Plausible Spatio-Temporal Adjustment For Training Deep Spiking Neural Networkscited by 22
  11. 2025How Can Time Series Analysis Benefit From Multiple Modalities? A Survey and Outlookcited by 20
  12. 2021Classical-to-Quantum Transfer Learning for Spoken Command Recognition Based on Quantum Neural Networkscited by 19
32 more
  1. 2022Low-Resource Music Genre Classification with Cross-Modal Neural Model Reprogrammingcited by 17
  2. 2021Temporal Knowledge Distillation for On-device Audio Classificationcited by 13
  3. 2023CWCL: Cross-Modal Transfer with Continuously Weighted Contrastive Losscited by 12
  4. 2024LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Unitscited by 11
  5. 2022Exploiting Low-Rank Tensor-Train Deep Neural Networks Based on Riemannian Gradient Descent With Illustrations of Speech Processingcited by 10
  6. 2021A Streaming End-to-End Framework For Spoken Language Understandingcited by 8
  7. 2021Bangla Natural Language Processing: A Comprehensive Analysis of Classical, Machine Learning, and Deep Learning Based Methodscited by 8
  8. 2022FedorAS: Federated Architecture Search under system heterogeneitycited by 4
  9. 2024Boosting keyword spotting through on-device learnable user speech characteristicscited by 4
  10. 2024A Backdoor Approach with Inverted Labels Using Dirty Label-Flipping Attackscited by 4
  11. 2021Neural Model Reprogramming with Similarity Based Mapping for Low-Resource Spoken Command Recognitioncited by 3
  12. 2022TB or not TB? Acoustic cough analysis for tuberculosis classificationcited by 3
  13. 2021Encoder-Decoder Neural Architecture Optimization for Keyword Spottingcited by 2
  14. 2021Attention-Free Keyword Spottingcited by 2
  15. 2023To Wake-up or Not to Wake-up: Reducing Keyword False Alarm by Successive Refinementcited by 2
  16. 2024Audio Enhancement for Computer Audition -- An Iterative Training Paradigm Using Sample Importancecited by 2
  17. 2022Exploiting Hybrid Models of Tensor-Train Networks for Spoken Command Recognitioncited by 1
  18. 2022Speech Augmentation Based Unsupervised Learning for Keyword Spottingcited by 1
  19. 2023Keyword spotting -- Detecting commands in speech using deep learningcited by 1
  20. 2021Real-time low-resource phoneme recognition on edge devicescited by 0
  21. 2021End-to-end Keyword Spotting using Xception-1dcited by 0
  22. 2022Heterogeneous Reservoir Computing Models for Persian Speech Recognitioncited by 0
  23. 2022A Quantum Kernel Learning Approach to Acoustic Modeling for Spoken Command Recognitioncited by 0
  24. 2023Employing Hybrid Deep Neural Networks on Dari Speechcited by 0
  25. 2024NUTS, NARS, and Speechcited by 0
  26. 2024Language-Universal Speech Attributes Modeling for Zero-Shot Multilingual Spoken Keyword Recognitioncited by 0
  27. 2024Contrastive Augmentation: An Unsupervised Learning Approach for Keyword Spotting in Speech Technologycited by 0
  28. 2025Vocal Tract Length Warped Features for Spoken Keyword Spottingcited by 0
  29. 2025Speech Command Recognition Using LogNNet Reservoir Computing for Embedded Systemscited by 0
  30. 2026PCOV-KWS: Multi-task Learning for Personalized Customizable Open Vocabulary Keyword Spottingcited by 0
  31. 2026SpeechGuard: Online Defense against Backdoor Attacks on Speech Recognition Modelscited by 0
  32. 2026Natural Backdoor Attacks on Speech Recognition Modelscited by 0