Paper Info
Title
AN ASYNCHRONOUS WFST-BASED DECODER FOR AUTOMATIC SPEECH RECOGNITION
Abstract
We introduce asynchronous dynamic decoder, which adopts an efficient A* algorithm to incorporate big language models in the one-pass decoding for large vocabulary continuous speech recognition. Unlike standard one-pass decoding with on-the-fly composition decoder which might induce a significant computation overhead, the asynchronous dynamic decoder has a novel design where it has two fronts, with one performing "exploration" and the other "backfill". The computation of the two fronts alternates in the decoding process, resulting in more effective pruning than the standard one-pass decoding with an on-the-fly composition decoder. Experiments show that the proposed decoder works notably faster than the standard one-pass decoding with on-the-fly composition decoder, while the acceleration will be more obvious with the increment of data complexity.
Year
DOI
Venue
2021
10.1109/ICASSP39728.2021.9414509
2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021)
Keywords
DocType
Citations 
Automatic speech recognition, decoder, lattice generation, lattice pruning
Conference
0
PageRank 
References 
Authors
0.34
5
6
Name
Order
Citations
PageRank
Hang Lv102.70
Zhehuai Chen220.72
Hainan Xu3145.56
Daniel Povey42442231.75
Lei Xie542564.87
Sanjeev Khudanpur62155202.00