15 citations · 15 across the 1 of their papers we have counts for
2 papers
cs.CL2020★ 15 cited
Voice trigger detection from LVCSR hypothesis lattices using bidirectional lattice recurrent neural networks
Woojay Jeon, Leo Liu, Henry Mason
We propose a method to reduce false voice triggers of a speech-enabled personal assistant by post-processing the hypothesis lattice of a server-side large-vocabulary continuous spe…
cs.LG2019
SNDCNN: Self-normalizing deep CNNs with scaled exponential linear units for speech recognition
Zhen Huang, Tim Ng, Leo Liu +3
Very deep CNNs achieve state-of-the-art results in both computer vision and speech recognition, but are difficult to train. The most popular way to train very deep CNNs is to use s…