Deterministic binary filters for keyword spotting applications
暂无分享,去创建一个
We present a binary architecture with 60% fewer parameters and 50% fewer operations during inference compared to the current state of the art for keyword spotting (KWS) applications at the cost of 3.4% accuracy. We construct convolutional filters on-the-fly using orthogonal binary codes and results in a compact architecture that would fit in devices with less than 30kB of memory.
[1] Fumiyuki Adachi,et al. Wideband DS-CDMA for next-generation mobile communications systems , 1998, IEEE Commun. Mag..
[2] Yundong Zhang,et al. Hello Edge: Keyword Spotting on Microcontrollers , 2017, ArXiv.