Max-pooling loss training of long short-term memory networks for small-footprint keyword spotting

SLT, Volume abs/1705.02411, 2016.

Cited by: 15|Bibtex|Views58|Links
EI

Abstract:

We propose a max-pooling based loss function for training Long Short-Term Memory (LSTM) networks for small-footprint keyword spotting (KWS), with low CPU, memory, and latency requirements. The max-pooling loss training can be further guided by initializing with a cross-entropy loss trained network. A posterior smoothing based evaluation a...More

Code:

Data:

Your rating :
0

 

Tags
Comments