A Channel-Pruned and Weight-Binarized Convolutional Neural Network for Keyword Spotting
We study channel number reduction in combination with weight binarization (1-bit weight precision) to trim a convolutional neural network for a keyword spotting (classification) task. We adopt a group-wise splitting method based on the group Lasso penalty to achieve over 50% channel sparsity while maintaining the network performance within 0.25% accuracy loss. We show an effective three-stage procedure to balance accuracy and sparsity in network training.
Code (0)
등록된 구현이 없습니다.
Tasks
BinarizationGeneral ClassificationKeyword SpottingSimilar Papers 제목 키워드 기반
DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search
The convolutional neural network has achieved great success in fulfilling computer vision tasks despite large computation overhead against efficient deployment. Structured (channel) pruning is usually applied to reduce t…
Neural Architecture SearchBDC-Occ: Binarized Deep Convolution Unit For Binarized Occupancy Network
Existing 3D occupancy networks demand significant hardware resources, hindering the deployment of edge devices. Binarized Neural Networks (BNN) offer substantially reduced computational and memory requirements. However, …
BinarizationOnDA: On-device Channel Pruning for Efficient Personalized Keyword Spotting
Always-on keyword spotting (KWS) demands on-device adaptation to cope with user- and environment-specific distribution shifts under tight latency and energy budgets. This paper proposes, for the first time, coupling weig…
Keyword SpottingBreakingBED -- Breaking Binary and Efficient Deep Neural Networks by Adversarial Attacks
Deploying convolutional neural networks (CNNs) for embedded applications presents many challenges in balancing resource-efficiency and task-related accuracy. These two aspects have been well-researched in the field of CN…
A 510-nW Wake-Up Keyword-Spotting Chip Using Serial-FFT-Based MFCC and Binarized Depthwise Separable CNN in 28-nm CMOS
We propose a sub-µW always-ON keyword spotting (µKWS) chip for audio wake-up systems. It is mainly composed of a neural network (NN) and a feature extraction (FE) circuit. For significantly reducing the memory footprin…
Keyword Spotting