Dynamic Frame Skipping for Fast Speech Recognition in Recurrent Neural Network Based Acoustic Models

ICASSP, pp. 4984-4988, 2018.

Cited by: 3|Bibtex|Views14
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com

Abstract:

A recurrent neural network is a powerful tool for modeling sequential data such as text and speech. While recurrent neural networks have achieved record-breaking results in speech recognition, one remaining challenge is their slow processing speed. The main cause comes from the nature of recurrent neural networks that read only one frame ...More

Code:

Data:

Your rating :
0

 

Tags
Comments