We also show that when our approach is used in conjunction with a max-pooling loss, we are able to improve relative false accepts by 25 % at a fixed latency when compared to cross entropy loss.
Wake word (WW) spotting is challenging in far-field not only because of the interference in signal transmission but also the complexity in acoustic environments.
In this paper, we propose two new methods for detecting the endpoints of wake words in neural KWS that use single-stage word-level neural networks.
We investigate low-bit quantization to reduce computational cost of deep neural network (DNN) based keyword spotting (KWS).
no code implementations • 21 Apr 2014 • Adam H. Marblestone, Evan R Daugharthy, Reza Kalhor, Ian D Peikon, Justus M Kebschull, Seth L Shipman, Yuriy Mishchenko, Je Hyuk Lee, Konrad P. Kording, Edward S. Boyden, Anthony M Zador, George M. Church
We propose a neural connectomics strategy called Fluorescent In-Situ Sequencing of Barcoded Individual Neuronal Connections (FISSEQ-BOINC), leveraging fluorescent in situ nucleic acid sequencing in fixed tissue (FISSEQ).
Neurons and Cognition