mlsanityData to 14 Oct 2026

Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting

arXiv 1703.05390 ↗First posted 15 Mar 2017cs.CL cs.AI cs.LGcited by 32

Not on the map. Why?

Abstract (arXiv)

Keyword spotting (KWS) constitutes a major component of human-technology interfaces. Maximizing the detection accuracy at a low false alarm (FA) rate, while minimizing the footprint size, latency and complexity are the goals for KWS. Towards achieving them, we study Convolutional Recurrent Neural Networks (CRNNs). Inspired by large-scale state-of-the-art speech recognition systems, we combine the strengths of convolutional layers and recurrent layers to exploit local structure and long-range context. We analyze the effect of architecture parameters, and propose training strategies to improve performance. With only ~230k parameters, our CRNN model yields acceptably low latency, and achieves 97.71% accuracy at 0.5 FA/hour for 5 dB signal-to-noise ratio.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 12; 2022: 8; 2023: 4; 2024: 3; 2025: 4; 2026: 1.

32 papers.

Sort:

By area:

  1. 2021Deep Spoken Keyword Spotting: An Overviewcited by 43
  2. 2021Learning Efficient Representations for Keyword Spotting with Triplet Losscited by 24
  3. 2021Temporal Knowledge Distillation for On-device Audio Classificationcited by 15
  4. 2021Visual Keyword Spotting with Attentioncited by 11
  5. 2023Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Reviewcited by 9
  6. 2021Synthetic Dataset Generation of Driver Telematicscited by 8
  7. 2021Tiny-CRNN: Streaming Wakeword Detection In A Low Footprint Settingcited by 5
  8. 2022Keyword Spotting System and Evaluation of Pruning and Quantization Methods on Low-power Edge Microcontrollerscited by 4
  9. 2022LiCo-Net: Linearized Convolution Network for Hardware-efficient Keyword Spottingcited by 4
  10. 2021FakeWake: Understanding and Mitigating Fake Wake-up Words of Voice Assistantscited by 3
  11. 2023Speech Understanding on Tiny Devices with A Learning Cachecited by 3
  12. 2025End-to-End Efficiency in Keyword Spotting: A System-Level Approach for Embedded Microcontrollerscited by 3
20 more
  1. 2025Elementary, My Dear Watson: Non-Invasive Neural Keyword Spotting in the LibriBrain Datasetcited by 3
  2. 2021End-to-end Keyword Spotting using Neural Architecture Search and Quantizationcited by 2
  3. 2021Encoder-Decoder Neural Architecture Optimization for Keyword Spottingcited by 2
  4. 2022Exploring Sequence-to-Sequence Transformer-Transducer Models for Keyword Spottingcited by 2
  5. 2023To Wake-up or Not to Wake-up: Reducing Keyword False Alarm by Successive Refinementcited by 2
  6. 2021Multi-task Learning with Cross Attention for Keyword Spottingcited by 1
  7. 2022A Fast Network Exploration Strategy to Profile Low Energy Consumption for Keyword Spottingcited by 1
  8. 2022Improving Voice Trigger Detection with Metric Learningcited by 1
  9. 2022Speech Augmentation Based Unsupervised Learning for Keyword Spottingcited by 1
  10. 2025RDI: An adversarial robustness evaluation metric for deep neural networks based on model statistical featurescited by 1
  11. 2021Neural Networks for Keyword Spotting on IoT Devicescited by 0
  12. 2021Real-time low-resource phoneme recognition on edge devicescited by 0
  13. 2022A Study of Designing Compact Audio-Visual Wake Word Spotting System Based on Iterative Fine-Tuning in Neural Network Pruningcited by 0
  14. 2022Frequency-centroid features for word recognition of non-native English speakerscited by 0
  15. 2023AraSpot: Arabic Spoken Command Spottingcited by 0
  16. 2024Hijacking Attacks against Neural Networks by Analyzing Training Datacited by 0
  17. 2024Temporal assessment of malicious behaviors: application to turnout field data monitoringcited by 0
  18. 2024Multitaper mel-spectrograms for keyword spottingcited by 0
  19. 2025Keyword Spotting with Hyper-Matched Filters for Small Footprint Devicescited by 0
  20. 2026Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computationscited by 0