Time-Delayed Bottleneck Highway Networks Using a DFT Feature for Keyword Spotting

Ken'ichi Kumatani
Ken'ichi Kumatani
Anirudh Raju
Anirudh Raju

ICASSP, pp. 5489-5493, 2018.

Cited by: 14|Bibtex|Views35|Links
EI

Abstract:

This paper presents a novel deep neural network (DNN) architecture with highway blocks (HWs) using a complex discrete Fourier transform (DFT) feature for keyword spotting. In our previous work, we showed that the feed-forward DNN with a time-delayed bottleneck layer (TDB-DNN) directly trained from the audio input outperformed the model wi...More

Code:

Data:

Your rating :
0

 

Tags
Comments