A Time Delay Neural Network with Shared Weight Self-Attention for Small-Footprint Keyword Spotting

	A Time Delay Neural Network with Shared Weight Self-Attention for Small-Footprint Keyword Spotting
	Ye Bai; Jiangyan Yi; Zhengqi Wen; Zhengkun Tian; Chenghao Zhao; Cunhang Fan
	2019
会议名称	interspeech
会议日期	2019
会议地点	graz
摘要	Keyword spotting requires a small memory footprint to run on mobile devices. However, previous works still use several hun- dred thousand parameters to achieve good performance. To ad- dress this issue, we propose a time delay neural network with shared weight self-attention for small-footprint keyword spot- ting. By sharing weights, the parameters of self-attention are reduced but without performance reduction. The publicly avail- able Google Speech Commands dataset is used to evaluate the models. The number of parameters (12K) of our model is 1/20 of state-of-the-art ResNet model (239K). The proposed model achieves an error rate of 4.19% , which is comparable to the ResNet model.
七大方向——子方向分类	语音识别与合成
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/44981
专题	多模态人工智能系统全国重点实验室_智能交互
作者单位	Institute of Automation, Chinese Academy of Sciences
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Ye Bai,Jiangyan Yi,Zhengqi Wen,et al. A Time Delay Neural Network with Shared Weight Self-Attention for Small-Footprint Keyword Spotting[C],2019.