Corpus ID: 25266153

A Cascade Architecture for Keyword Spotting on Mobile Devices

@article{Gruenstein2017ACA,
  title={A Cascade Architecture for Keyword Spotting on Mobile Devices},
  author={A. Gruenstein and R. Alvarez and C. Thornton and Mohammadali Ghodrat},
  journal={ArXiv},
  year={2017},
  volume={abs/1712.03603}
}
  • A. Gruenstein, R. Alvarez, +1 author Mohammadali Ghodrat
  • Published 2017
  • Computer Science, Engineering
  • ArXiv
  • We present a cascade architecture for keyword spotting with speaker verification on mobile devices. By pairing a small computational footprint with specialized digital signal processing (DSP) chips, we are able to achieve low power consumption while continuously listening for a keyword. 

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    Self quotient image for face recognition
    156
    Hybrid Transformer/CTC Networks for Hardware Efficient Voice Triggering
    Learning to Detect Keyword Parts and Whole by Smoothed Max Pooling
    1
    Small Footprint Multi-channel Keyword Spotting
    Surprisal-Triggered Conditional Computation with Neural Networks
    1
    Training Keyword Spotting Models on Non-IID Data with Federated Learning
    1
    End-to-end Streaming Keyword Spotting
    6
    Low-Bit Quantization and Quantization-Aware Training for Small-Footprint Keyword Spotting
    1
    End-to-End Streaming Keyword Spotting
    15

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 11 REFERENCES
    Sensory functioning and intelligence in old age: a strong connection.
    896
    The GTP binding protein Obg homolog ObgE is involved in ribosome maturation
    128
    Introduction to Digital Filters: with Audio Applications
    288
    The B-matrix must be rotated when correcting for subject motion in DTI data.
    989
    End-to-end text-dependent speaker verification
    308
    On the Efficient Representation and Execution of Deep Acoustic Models
    25
    Automatic Gain Control and Multi-style Training for Robust Small-Footprint Keyword Spotting with Deep
    • 2015