Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

ACCELERATING RECURRENT NEURAL NETWORK LANGUAGE MODEL BASED ONLINE SPEECH RECOGNITION SYSTEM

Abstract: 

This paper presents methods to accelerate recurrent neural network based language models (RNNLMs) for online speech recognition systems.
Firstly, a lossy compression of the past hidden layer outputs (history vector) with caching is introduced in order to reduce the number of LM queries.
Next, RNNLM computations are deployed in a CPU-GPU hybrid manner, which computes each layer of the model on a more advantageous platform.
The added overhead by data exchanges between CPU and GPU is compensated through a frame-wise batching strategy.
The performance of the proposed methods evaluated on LibriSpeech1 test sets indicates that the reduction in history vector precision improves the average recognition speed by 1.23 times with minimum degradation in accuracy.
On the other hand, the CPU-GPU hybrid parallelization enables RNNLM based real-time recognition with a four times improvement in speed.

up
0 users have voted:

Paper Details

Authors:
Chiyoun Park, Namhoon Kim, Jaewon Lee
Submitted On:
26 April 2018 - 1:10am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Kyungmin Lee
Paper Code:
SP-P19.3
Document Year:
2018
Cite

Document Files

Icassp2018_KML_20180402_poster.pdf

(81 downloads)

Subscribe

[1] Chiyoun Park, Namhoon Kim, Jaewon Lee, "ACCELERATING RECURRENT NEURAL NETWORK LANGUAGE MODEL BASED ONLINE SPEECH RECOGNITION SYSTEM", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3183. Accessed: Sep. 18, 2018.
@article{3183-18,
url = {http://sigport.org/3183},
author = {Chiyoun Park; Namhoon Kim; Jaewon Lee },
publisher = {IEEE SigPort},
title = {ACCELERATING RECURRENT NEURAL NETWORK LANGUAGE MODEL BASED ONLINE SPEECH RECOGNITION SYSTEM},
year = {2018} }
TY - EJOUR
T1 - ACCELERATING RECURRENT NEURAL NETWORK LANGUAGE MODEL BASED ONLINE SPEECH RECOGNITION SYSTEM
AU - Chiyoun Park; Namhoon Kim; Jaewon Lee
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3183
ER -
Chiyoun Park, Namhoon Kim, Jaewon Lee. (2018). ACCELERATING RECURRENT NEURAL NETWORK LANGUAGE MODEL BASED ONLINE SPEECH RECOGNITION SYSTEM. IEEE SigPort. http://sigport.org/3183
Chiyoun Park, Namhoon Kim, Jaewon Lee, 2018. ACCELERATING RECURRENT NEURAL NETWORK LANGUAGE MODEL BASED ONLINE SPEECH RECOGNITION SYSTEM. Available at: http://sigport.org/3183.
Chiyoun Park, Namhoon Kim, Jaewon Lee. (2018). "ACCELERATING RECURRENT NEURAL NETWORK LANGUAGE MODEL BASED ONLINE SPEECH RECOGNITION SYSTEM." Web.
1. Chiyoun Park, Namhoon Kim, Jaewon Lee. ACCELERATING RECURRENT NEURAL NETWORK LANGUAGE MODEL BASED ONLINE SPEECH RECOGNITION SYSTEM [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3183