Corpus ID: 221585948

Hardware Aware Training for Efficient Keyword Spotting on General Purpose and Specialized Hardware

@article{Blouw2020HardwareAT,
  title={Hardware Aware Training for Efficient Keyword Spotting on General Purpose and Specialized Hardware},
  author={Peter Blouw and G. Malik and Benjamin Morcos and Aaron R. Voelker and C. Eliasmith},
  journal={ArXiv},
  year={2020},
  volume={abs/2009.04465}
}
  • Peter Blouw, G. Malik, +2 authors C. Eliasmith
  • Published 2020
  • Computer Science, Engineering, Mathematics
  • ArXiv
  • Keyword spotting (KWS) provides a critical user interface for many mobile and edge applications, including phones, wearables, and cars. As KWS systems are typically 'always on', maximizing both accuracy and power efficiency are central to their utility. In this work we use hardware aware training (HAT) to build new KWS neural networks based on the Legendre Memory Unit (LMU) that achieve state-of-the-art (SotA) accuracy and low parameter counts. This allows the neural network to run efficiently… CONTINUE READING
    1 Citations

    Figures and Tables from this paper

    TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices
    • 4
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 19 REFERENCES
    Laika: A 5uW Programmable LSTM Accelerator for Always-on Keyword Spotting in 65nm CMOS
    • J. S. Giraldo, M. Verhelst
    • Computer Science
    • ESSCIRC 2018 - IEEE 44th European Solid State Circuits Conference (ESSCIRC)
    • 2018
    • 22
    14.1 A 510nW 0.41V Low-Memory Low-Computation Keyword-Spotting Chip Using Serial FFT-Based MFCC and Binarized Depthwise Separable Convolutional Neural Network in 28nm CMOS
    • 5
    • Highly Influential
    Vocell: A 65-nm Speech-Triggered Wake-Up SoC for 10- $\mu$ W Keyword Spotting and Speaker Verification
    • 3
    • Highly Influential
    Streaming keyword spotting on mobile devices
    • 5
    • Highly Influential
    • PDF
    TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices
    • 4
    • PDF
    SRAM for Error-Tolerant Applications With Dynamic Energy-Quality Management in 28 nm CMOS
    • 44
    • PDF
    A 65 nm 1.0 V 1.84 ns Silicon-on-Thin-Box (SOTB) embedded SRAM with 13.72 nW/Mbit standby power for smart IoT
    • 3
    How to Achieve World-Leading Energy Efficiency using 22FDX with Adaptive Body Biasing on an Arm Cortex-M4 IoT SoC
    • 4
    Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks
    • 20
    • PDF