Broadcasted Residual Learning For Efficient Keyword Spotting

Abstract

Keyword spotting is an important research field because it plays a key role in device wake-up and user interaction on smart devices. However, it is challenging to minimize errors while operating efficiently in devices with limited resources such as mobile phones. We present a broadcasted residual learning method to achieve high accuracy with small model size and computational load. Our method configures most of the residual functions as 1D temporal convolution while still allows 2D convolution together using a broadcasted-residual connection that expands temporal output to frequency-temporal dimension. This residual mapping enables the network to effectively represent useful audio features with much less computation than conventional convolutional neural networks. We also propose a novel network architecture, Broadcasting-residual network (BC-ResNet), based on broadcasted residual learning and describe how to scale up the model according to the target device's resources. BC-ResNets ach

Stats

• citations89
• S2 citations—
• github stars93
• HF likes0
• heat score18.60
• arxiv keykim2021broadcasted

Related papers

• Deep Residual Learning For Small-footprint Keyword Spotting (2017)16.21
• Small-footprint Keyword Spotting With Graph Convolutional Network (2019)10.48
• Predicting Detection Filters For Small Footprint Open-vocabulary Keyword Spotting (2019)9.92
• Streaming Small-footprint Keyword Spotting Using Sequence-to-sequence Models (2017)12.40
• A Separable Temporal Convolution Neural Network With Attention For Small-footprint Keyword Spotting (2021)0.00
• Small-footprint Open-vocabulary Keyword Spotting With Quantized LSTM Networks (2020)0.00
• Temporal Convolution For Real-time Keyword Spotting On Mobile Devices (2019)15.67
• End-to-end Streaming Keyword Spotting (2018)12.10