A Separable Temporal Convolution Neural Network With Attention For Small-footprint Keyword Spotting

Abstract

Keyword spotting (KWS) on mobile devices generally requires a small memory footprint. However, most current models still maintain a large number of parameters in order to ensure good performance. To solve this problem, this paper proposes a separable temporal convolution neural network with attention, it has a small number of parameters. Through the time convolution combined with attention mechanism, a small number of parameters model (32.2K) is implemented while maintaining high performance. The proposed model achieves 95.7% accuracy on the Google Speech Commands dataset, which is close to the performance of Res15(239K), the state-of-the-art model in KWS at present.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhu2021a

Related papers

• Separable Temporal Convolution Plus Temporally Pooled Attention For Lightweight High-performance Keyword Spotting (2021)0.00
• Temporal Convolution For Real-time Keyword Spotting On Mobile Devices (2019)15.67
• Small-footprint Keyword Spotting With Multi-scale Temporal Convolution (2020)0.00
• Depthwise Separable Convolutional Resnet With Squeeze-and-excitation Blocks For Small-footprint Keyword Spotting (2020)11.29
• Small-footprint Keyword Spotting With Graph Convolutional Network (2019)10.48
• Small-footprint Keyword Spotting Using Deep Neural Network And Connectionist Temporal Classifier (2017)0.00
• Neural ODE With Temporal Convolution And Time Delay Neural Networks For Small-footprint Keyword Spotting (2020)0.00
• Predicting Detection Filters For Small Footprint Open-vocabulary Keyword Spotting (2019)9.92