mlsanityData to 14 Oct 2026

End-to-end Keyword Spotting using Neural Architecture Search and Quantization

arXiv 2104.06666 ↗First posted 14 Apr 2021cs.SD cs.LG eess.AScited by 2

Not on the map. Why?

Abstract (arXiv)

This paper introduces neural architecture search (NAS) for the automatic discovery of end-to-end keyword spotting (KWS) models in limited resource environments. We employ a differentiable NAS approach to optimize the structure of convolutional neural networks (CNNs) operating on raw audio waveforms. After a suitable KWS model is found with NAS, we conduct quantization of weights and activations to reduce the memory footprint. We conduct extensive experiments on the Google speech commands dataset. In particular, we compare our end-to-end approach to mel-frequency cepstral coefficient (MFCC) based systems. For quantization, we compare fixed bit-width quantization and trained bit-width quantization. Using NAS only, we were able to obtain a highly efficient model with an accuracy of 95.55% using 75.7k parameters and 13.6M operations. Using trained bit-width quantization, the same model achieves a test accuracy of 93.76% while using on average only 2.91 bits per activation and 2.51 bits per weight.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 24 of its 35 references that are in the map. First posted on arXiv 14 Apr 2021.

Builds on

24 of 35 references.

References · 24

  1. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  2. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  3. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  4. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
  5. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 837
  6. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
  7. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
  8. 2019Learned Step Size Quantizationcited by 628
  9. 2017State-of-the-art Speech Recognition With Sequence-to-Sequence Modelscited by 196
  10. 2017Hierarchical Representations for Efficient Architecture Searchcited by 191
  11. 2018Speaker Recognition from Raw Waveform with SincNetcited by 166
  12. 2017Hello Edge: Keyword Spotting on Microcontrollerscited by 110
12 more
  1. 2019Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networkscited by 90
  2. 2019SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollerscited by 52
  3. 2020TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aidscited by 42
  4. 2017Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spottingcited by 32
  5. 2019Small-Footprint Keyword Spotting on Raw Audio Data with Sinc-Convolutionscited by 20
  6. 2019Mixed Precision DNNs: All you need is a good parametrizationcited by 18
  7. 2017Max-Pooling Loss Training of Long Short-Term Memory Networks for Small-Footprint Keyword Spottingcited by 15
  8. 2020Neural Architecture Search For Keyword Spottingcited by 11
  9. 2020AutoKWS: Keyword Spotting with Differentiable Architecture Searchcited by 10
  10. 2017Deep Convolutional Neural Network Inference with Floating-point Weights and Fixed-point Activationscited by 7
  11. 2017Honk: A PyTorch Reimplementation of Convolutional Neural Networks for Keyword Spottingcited by 6
  12. 2020Resource-efficient DNNs for Keyword Spotting using Neural Architecture Search and Quantizationcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 2.

2 papers.

  1. 2022Filterbank Learning for Noise-Robust Small-Footprint Keyword Spottingcited by 3
  2. 2022A Multi-tasking Model of Speaker-Keyword Classification for Keeping Human in the Loop of Drone-assisted Inspectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Sub 8-Bit Quantization of Streaming Keyword Spotting Models for Embedded Chipsets
  2. 2022Keyword Spotting System and Evaluation of Pruning and Quantization Methods on Low-power Edge Microcontrollers
  3. 2022BiFSMN: Binary Neural Network for Keyword Spotting
  4. 2022BiFSMNv2: Pushing Binary Neural Networks for Keyword Spotting to Real-Network Performance
  5. 2023SimQ-NAS: Simultaneous Quantization Policy and Neural Architecture Search
  6. 2022Sub-mW Keyword Spotting on an MCU: Analog Binary Feature Extraction and Binary Neural Networks
  7. 20214-bit Quantization of LSTM-based Speech Recognition Models
  8. 2024GE2E-KWS: Generalized End-to-End Training and Evaluation for Zero-shot Keyword Spotting